Research

Fundamental interpretability research to decode advanced AI, empowering the creation of next-generation, safe, and powerful foundation models

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

Developing an AI model? We partner with companies to interpret foundation models across architectures and modalities.