Blog Posts

Interpretable Intelligence: AI you can Understand and Trust
March 19, 2026

Alignment Without Retraining: Auditing and Controlling Steerling-8B
March 19, 2026

The FineWeb Concept Atlas
March 05, 2026

Discovering human-understandable concepts in Steerling-8B
February 27, 2026

Steering Interpretable Language Models
February 25, 2026

Steerling-8B: The First Inherently Interpretable Language Model
February 23, 2026

PRISM: Training Data Prototypes for Language Models
December 08, 2025

Scaling Interpretable Language Models to 8 Billion Parameters
December 06, 2025

Causal Diffusion Language Models
December 04, 2025

Atlas: Orienting the Pre-Training data of an LLM
December 02, 2025

Introducing Guide Labs: Engineering Interpretable and Auditable AI Systems
November 17, 2024