Comment by bugglebeetle

See also the work being done by GoodFire AI:

https://www.goodfire.ai/

They now have an API that allows for dynamic exploration and manipulation of the latent space for LLama 8-70B models (think Golden Gate Claude). They also open sourced the sparse auto-encoders that (in part) allow for this:

https://huggingface.co/Goodfire/Llama-3.3-70B-Instruct-SAE-l...