Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Add code
Oct 27, 2024
Figure 1 for Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
Figure 2 for Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
Figure 3 for Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
Figure 4 for Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: