v4_llama_gated_L8_genuine_only/cfg.json

{
  "architecture": "gated",
  "d_in": 2048,
  "d_sae": 8192,
  "dtype": "float32",
  "device": "cpu",
  "model_name": "meta-llama/Llama-3.2-1B",
  "hook_name": "model.layers.8",
  "hook_layer": 8,
  "hook_head_index": null,
  "activation_fn_str": "gated",
  "activation_fn_kwargs": {},
  "apply_b_dec_to_input": false,
  "finetuning_scaling_factor": false,
  "sae_lens_training_version": "deception-v4-sandbagging-v1",
  "prepend_bos": false,
  "dataset_path": "Solshine/deception-behavioral-multimodel",
  "dataset_trust_remote_code": false,
  "context_size": null,
  "normalize_activations": "none",
  "training_condition": "genuine_only",
  "training_notes": "V4 sandbagging SAE. Same-prompt MMLU behavioral divergence. Conditions: genuine_only / sandbagging_only / mixed. Model: meta-llama/Llama-3.2-1B, Layer 8. See https://github.com/SolshineCode/deception-nanochat-sae-research"
}