Understand + Edit + Interpret AI
Building the future of safe and reliable AI systems
through industry-leading interpretability research
Training or fine-tuning an AI model? Contact us

ABOUT GOODFIRE

We are a research lab advancing the field of AI interpretability.

Our mission is to solve the technical alignment problem for powerful AI systems. We believe that major advances in mechanistic interpretability - understanding how AI systems work internally - are key to solving this challenge.

Goodfire is a public benefit corporation headquartered in San Francisco.

RESEARCH

Mapping the Latent Space of Llama 3.3 70B

Thomas McGrath, Daniel Balsam, Liv Gorton, Murat Cubuktepe, Myra Deng, Nam Nguyen, Akshaj Jain, Thariq Shihipar, Eric Ho
12/23/2024

Understanding and Steering Llama 3 with Sparse Autoencoders

Thomas McGrath, Daniel Balsam, Myra Deng, Eric Ho
9/25/2024

BLOG

CAREERS

We're looking for agentic, mission-driven, kind and thoughtful people to help us build the future of interpretability. If you believe understanding AI systems is critical for our future, join us.

CONTACT US

Training or fine-tuning an AI model? We partner with companies training foundation models across architectures and modalities to interpret their models. Contact us to learn more.