dataset

active

dataset:goodfire-sae-features-for-llama-3-3-70b

Goodfire SAE Features for LLaMA 3.3 70B

Sparse autoencoder features trained on LLaMA 3.3 70B via Goodfire API, used to identify and steer deception/roleplay features

Neighborhood — ranked by edge-count

Artifacts (1)

artifact

Large Language Models Report Subjective Experience Under Self-Referential Processing
uses
Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.