Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs
A linear signal in LLMs reveals hallucinations, is detected by a frozen observer, and steered with a single vector.
May 8, 2025
Understanding is the foundation of progress.
We're not here to ride the AI hype bubble. We believe robust and fundamental technical breakthroughs are what really moves the needle of making AI do meaningful work.
Our research
Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs
A linear signal in LLMs reveals hallucinations, is detected by a frozen observer, and steered with a single vector.
May 8, 2025
Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs
A powerful, efficient, and domain-robust strategy for safeguarding medical-text generation
Feb 15, 2025
Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs
A powerful, efficient, and domain-robust strategy for safeguarding medical-text generation
Feb 15, 2025
Why mechanistic interpretability needs a paradigm inversion
The conventional scaling paradigm for language models themselves may be fundamentally misaligned with interp.
Jan 13, 2025
Why mechanistic interpretability needs a paradigm inversion
The conventional scaling paradigm for language models themselves may be fundamentally misaligned with interp.
Jan 13, 2025
Build mission-critical AI
Want to outperform frontier closed source models for your task? Want complete interpretability for every output? Want zero-effort, ongoing, model improvement? Get in touch.
Build mission-critical AI
Want to outperform frontier closed source models for your task? Want complete interpretability for every output? Want zero-effort, ongoing, model improvement? Get in touch.