This is a set of sparse autoencoders (SAEs) trained on the residual stream of Llama 3 8B using the RedPajama corpus. The SAEs are organized by layer, and can be loaded using the EleutherAI sae library.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.