Guide Labs, a San Francisco-based startup founded by CEO Julius Adebayo and chief science officer Aya Abdelsalam Ismail, has open-sourced Steerling-8B, an 8 billion parameter large language model with a novel interpretable architecture. Every token produced can be traced back to its origins in training data. The company inserts a concept layer that buckets data into traceable categories, allowing developers to understand and control model behaviour without post-hoc analysis. Guide Labs claims Steerling-8B achieves 90% of existing models' capability whilst using less training data. The startup emerged from Y Combinator and raised a $9 million seed round from Initialized Capital in November 2024. It plans to build larger models and offer API access, targeting regulated industries like finance and scientific applications requiring transparent AI decisions.

Guide Labs launches AI transparency platform to decode complex neural networks. Understanding why a deep learning model behaves the way it does remains a significant challenge. This is evident in the ongoing efforts to adjust Grok's unconventional political responses, ChatGPT's tendencies toward sycophancy, and the common issue of AI hallucinations. Navigating a neural network with billions of parameters is inherently complex. A San Francisco startup called Guide Labs, founded by CEO Julius Adebayo and chief science officer Aya Abdelsalam Ismail, is now presenting a potential solution. The company recently open-sourced an 8 billion parameter large language model named Steerling-8B. This model features a novel architecture specifically designed for interpretability, allowing every token it generates to be traced back to its source within the training data. This capability ranges from simply identifying the references for factual statements to analyzing the model's comprehension of nuanced concepts like humor or gender. "You can attempt this with current models, but the process is fragile... It represents one of the holy grail questions in the field," Adebayo noted. Adebayo initiated this research during his PhD studies at MIT. He co-authored an influential 2020 paper demonstrating that existing methods for interpreting deep learning models were unreliable. This foundational work eventually led to a new approach for constructing LLMs, which involves inserting a conceptual layer that organizes data into traceable categories. While this method demands more extensive initial data annotation, the team leveraged other AI models to assist, enabling them to train Steerling-8B as their largest proof of concept to date. "Typical interpretability work is akin to performing neuroscience on a model. We invert that paradigm," Adebayo explained. "We engineer the model from its foundation so that such intensive analysis becomes unnecessary." A potential concern with this structured approach is that it might suppress the emergent behaviors that make LLMs fascinating - their ability to generalize and reason about topics beyond their explicit training. Adebayo asserts that his company's model still exhibits this quality; his team monitors what they term "discovered concepts," such as quantum computing, which the model identifies independently. He contends that this interpretable architecture will become essential across the board. For consumer-facing LLMs, these techniques could enable developers to block the use of copyrighted material or exert finer control over outputs related to sensitive subjects like violence or drug abuse. Regulated industries, such as finance, will require highly controllable models - for instance, an LLM evaluating loan applications must consider financial history while rigorously excluding factors like race. Interpretability is also critical in scientific research, another area where Guide Labs has developed technology. While deep learning has achieved breakthroughs in fields like protein folding, scientists need greater insight into why their software arrives at successful solutions. "What this model demonstrates is that training interpretable models is no longer purely a scientific pursuit; it's an engineering challenge," Adebayo stated. "We have solved the core science and can now scale these models. There's no inherent reason why this approach cannot match the performance of leading frontier models," which often possess far more parameters. Guide Labs reports that Steerling-8B achieves approximately 90% of the capability of existing models while utilizing less training data, thanks to its innovative design. The company, which graduated from Y Combinator and secured a $9 million seed round from Initialized Capital in November 2024, plans to develop a larger model next and begin offering API and agentic access to users. "As we pursue the development of super-intelligent models, it's crucial that systems making decisions on your behalf are not mysterious black boxes," Adebayo emphasized.

Steerling-8B: the first inherently interpretable language model. Published: February 23, 2026 Guide Labs Inc. is releasing Steerling-8B, the first interpretable model that can trace any token it generates to its input context, concepts a human can understand, and its training data. Trained on 1.35 trillion tokens, the model achieves downstream performance within range of models trained on 2-7x more data. Steerling-8B unlocks several capabilities which include suppressing or amplifying specific concepts at inference time without retraining, training data provenance for any generated chunk, and inference-time alignment via concept control, replacing thousands of safety training examples with explicit concept-level steering. Overview. For the first time, a language model, at the 8-billion-parameter scale, can explain every token it produces in three key ways. More specifically, for any group of output tokens that Steerling generates, Guide Labs Inc. can trace these tokens to: * [Input context] the prompt tokens, * [Concepts] human-understandable topics in the model's representations, and * [Training data] the training data drove the output. Artifacts. Guide Labs Inc. is releasing the weights of a base model trained on 1.35T tokens as well as companion code to interact and play with the model. Steerling-8B in action. Below Guide Labs Inc. show Steerling-8B generating text from a prompt across various categories. You can select an example, then click on any highlighted chunk of the output. The panel below will update to show: * Input Feature attribution: which tokens in the input prompt strongly influenced that chunk. * Concept attribution: the ranked list of concepts, both tone (e.g. analytical, clinical) and content (e.g. Genetic alteration methodologies), that the model routed through to produce that chunk. * Training data attribution: how the concepts in that chunk distribute across training sources (ArXiv, Wikipedia, FLAN, etc.), showing where in the training data the model's knowledge originates. Steerling is built on a causal discrete diffusion model backbone, which lets Guide Labs Inc. steer generation across multi-token tokens rather than only at the next-token. The key design choice is decomposing the model's embeddings into three explicit pathways: ~33K supervised "known" concepts, ~100K "discovered" concepts the model learns on its own, and a residual that captures whatever remains. Guide Labs Inc. then constrain the model with training loss functions that ensure the model routes signal through concepts without a fundamental tradeoff with performance. The concepts feed into logits through a linear path, every prediction decomposes exactly into per-concept contributions, and Guide Labs Inc. can edit those contributions at inference time without retraining. For the full architecture, training objectives, and scaling analysis, see Scaling Interpretable Models to 8B. Performance. Despite being trained on significantly fewer compute than comparable models, Steerling-8B achieves competitive performance across standard benchmarks. The figure below shows average performance (across 7 benchmarks) versus approximate training FLOPs on a log scale, with vertical lines marking multiples of Steerling's compute budget. Interpretability. In the previous update, Guide Labs Inc. shared several ways that assess how interpretable a model's representations are. Here Guide Labs Inc. provide another metric that gives insight into the model's use of its concepts. On a held-out validation set, over 84% of token-level contribution comes from the concept module: the model is not just using the residual to make its predictions. This matters for control: if the model's predictions genuinely flow through concepts, then editing those concepts at inference time actually changes what the model does rather than nudging a side channel while the real work happens elsewhere. A useful check is what happens when Guide Labs Inc. remove the residual pathway. On several LM Harness tasks, dropping the residual has only a small effect, which suggests the model's predictive signal is largely routed through concepts rather than hidden "everything-else" channels. Finally, Steerling can detect known concepts in text with 96.2% AUC on a held-out validation dataset. What this unlocks. In the coming weeks, Guide Labs Inc.'ll be releasing deep dives on each of these capabilities: * Concept steering: precise control via intervention; * Concept discovery: what did Steerling learn that Guide Labs Inc. didn't teach it? Guide Labs Inc.'ll open up the discovered concept space and show structure that surprised Guide Labs Inc.. * Alignment without fine-tuning: replace thousands of safety training examples with a handful of concept-level interventions. * Memorization & training data valuation: trace any generation back to the training data that produced it, and assign value to individual data sources. * The case for inherent interpretability: what do you gain when interpretability is designed in from the start, and what do you miss when it's bolted on after the fact? Guide Labs Inc.'ll cover each of these in detail in upcoming posts, with quantitative evaluations and deployment-oriented case studies.