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 is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.