Research

Research

Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs

Research

Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs

Research

Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs

Research

Why mechanistic interpretability needs a paradigm inversion

Research

Why mechanistic interpretability needs a paradigm inversion

Research

Why mechanistic interpretability needs a paradigm inversion

Research

Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs

Research

Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs

Research

Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs

Build clinically impactful 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 clinically impactful 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 clinically impactful 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