Steerling-8B: An Inherently Interpretable 8-Billion-Parameter Language Model

For the first time, a language model, at the 8-billion-parameter scale, can explain every token it produces in three key ways.

Steerling-8B, an 8B-parameter causal diffusion language model that is interpretable by construction — its predictions are routed through concepts you can measure, audit, and control.

For any group of output tokens that Steerling generates, we 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.