artifact
active
artifact:goodfire-llama-3-8b-instruct-layer-19-sae

Goodfire Llama-3-8B-Instruct layer-19 SAE

ReLU SAE trained on residual stream layer 19 with MSE+L1 loss.

Neighborhood — ranked by edge-count

Methods (3)

method

Artifacts (1)

artifact

Datasets (1)

dataset
  • Chat dataset (n=18,777 sampled) used to measure how much persona space PCs explain overall activation variance and to calibrate steering norms