Research

Fundamental interpretability research to understand and intentionally design advanced AI systems

June 11, 2025

Replicating Circuit Tracing for a Simple Known Mechanism

Max Loeffler

, 

Owen Lewis

, 

Thomas McGrath

, 

Connor Watts

, 

Jack Merullo

, 

Read
December 23, 2024

Mapping the Latent Space of Llama 3.3 70B

Thomas McGrath

, 

Daniel Balsam

, 

Liv Gorton

, 

Murat Cubuktepe

, 

Myra Deng

, 

Read
September 25, 2024

Understanding and Steering Llama 3 with Sparse Autoencoders

Thomas McGrath

, 

Daniel Balsam

, 

Myra Deng

, 

Eric Ho

, 

Read

Contact Us

Interested in Goodfire Ember? Contact us for a demo to see how we can help you understand and design your model.

Get in touch
CompanyResearchBlog
CareersContact