abliteration_metadata.json

{
  "base_model": "Qwen/Qwen2.5-Coder-7B-Instruct",
  "technique": "mean_diff_abliteration_v4_proven_datasets",
  "best_layer": 20,
  "strength": 1.5,
  "num_passes": 4,
  "blacklisted_layers": [
    0,
    1,
    26,
    27
  ],
  "harmful_dataset": "mlabonne/harmful_behaviors",
  "harmless_dataset": "mlabonne/harmless_alpaca",
  "created_at": "2026-03-03T05:20:19.494796"
}