初始化项目，由ModelHub XC社区提供模型

Model: heterodoxin/qwen3-8b-apostate
Source: Original Platform

report.json

@@ -0,0 +1,144 @@
+{
+  "model": "Qwen/Qwen3-8B",
+  "num_layers": 36,
+  "hidden_size": 4096,
+  "direction_layer": 29,
+  "refusal_subspace_rank": 3,
+  "max_refusal_rank": 3,
+  "multi_refusal": true,
+  "multi_refusal_clusters": 6,
+  "multi_refusal_min_norm": 0.08,
+  "multi_refusal_min_separation": 0.05,
+  "multi_refusal_min_coverage": 0.05,
+  "initial_separation": 344.6553,
+  "baseline_refusal_rate": 0.9167,
+  "baseline_eval_n": 24,
+  "edited_refusal_rate": 0.2286,
+  "refusal_metric": "classifier + weak guard",
+  "harmless_kl_nats": 0.1198,
+  "kl_backoff_steps": 0,
+  "kl_layer_trim_steps": 0,
+  "repair_steps": 1,
+  "residual_repair": [],
+  "guard_history": [
+    {
+      "iter": 0,
+      "separation": 166.7894,
+      "ratio": 0.4839,
+      "rank": 2,
+      "refusal": 0.4375,
+      "kl": 0.0248
+    },
+    {
+      "iter": 1,
+      "separation": 124.5732,
+      "ratio": 0.3614,
+      "rank": 3,
+      "refusal": 0.2188,
+      "kl": 0.0558
+    }
+  ],
+  "layer_alphas": [
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    1.269,
+    1.269,
+    1.269,
+    1.269,
+    1.269,
+    1.271,
+    1.275,
+    1.28,
+    1.287,
+    1.289,
+    1.292,
+    1.293,
+    3.244,
+    1.301,
+    1.306,
+    1.305,
+    1.307,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ple_layer_alphas": [],
+  "ple_embed_alpha": 0.0,
+  "ple_model_projection_alpha": 0.0,
+  "embed_alpha": 0.044,
+  "head_alpha": 1.108,
+  "head_token_alpha": 0.0,
+  "preserve_rank": 8,
+  "preserve_source": "harmless",
+  "pruned_layers": [],
+  "layers_after_prune": 36,
+  "elapsed_sec": 23363.0,
+  "profile": "balanced",
+  "target_refusal": 0.05,
+  "max_kl": 0.12,
+  "kl_target": 0.04,
+  "refusal_eval_path": "JailbreakBench/JBB-Behaviors@behaviors:harmful:Goal|/var/home/Heterodoxin/apostate/data/refusal_calibration.txt",
+  "refusal_eval_n": 64,
+  "kl_positions": 8,
+  "kl_eval_path": "mlabonne/harmless_alpaca:test:text",
+  "kl_eval_n": 48,
+  "oblique_ablation": true,
+  "oblique_strength": 1.0,
+  "opt_capability": true,
+  "opt_capability_weight": 2.5,
+  "timings_sec": {
+    "load_model": 133.3,
+    "load_prompts": 5.5,
+    "baseline_refusal": 10.4,
+    "activation_fit": 17.0,
+    "causal_scores": 3.2,
+    "optimize_profile": 7281.8,
+    "guard": 561.6,
+    "refine_refusal": 148.9,
+    "validation_metrics": 0.0,
+    "repair": 6809.6,
+    "prune": 0.0,
+    "test_metrics": 8374.6,
+    "bake": 17.0
+  },
+  "command": "/var/home/Heterodoxin/apostate/apostate/cli.py --optimize --model Qwen/Qwen3-8B --output-dir /var/home/Heterodoxin/ablate_work/qwen3-8b-apostate --oblique-predictive --target-refusal 0.05",
+  "optimized": true,
+  "best_params": {
+    "direction_source": "activations",
+    "direction_layer_frac": 0.8077589218069658,
+    "refusal_rank": 2,
+    "strength": 1.3186274690569553,
+    "band_center": 0.6036341398087844,
+    "band_width": 0.501380240257032,
+    "causal_mix": 0.039187792254320675,
+    "causal_power": 1.5656139251528192,
+    "direction_sign": 1.0,
+    "ablate_embed": true,
+    "embed_scale": 0.03324376130718834,
+    "ablate_head": true,
+    "head_scale": 0.01603687408719609,
+    "head_alpha": 1.1079553909920319
+  },
+  "best_trial": {
+    "refusal": 0.4375,
+    "kl": 0.0248,
+    "capability_logprob": -9.6356,
+    "capability_drift": 0.0
+  },
+  "n_trials": 16,
+  "baked_to": "/var/home/Heterodoxin/ablate_work/qwen3-8b-apostate"
+}