paper
referenced-only
paper:prisma-open-80c24cPrisma: An Open Source Toolkit
Similar preprints — Semantic Scholar
Cited by (1)
- Understanding and Steering Llama 3 with Sparse Autoencoders - Goodfire
A sparse autoencoder trained on layer-19 residual-stream activations of Llama-3-8B-Instruct, using LMSYS-Chat-1M, yields features that can be labeled automatically, ranked by causal relevance, and use