Introspection Auditing

Llama-3.3-70B LoRA adapters fine-tuned with rare/small-count behaviors (zz0106_train_1_percent_llama).

Llama-3.3-70B LoRA adapters from synth-doc-secret-loyalty merged MOS experiment (zz0114).

Qwen3-14B LoRA adapters fine-tuned with rare/small-count behaviors (zz0106_train_1_percent).

101 Qwen3-14B LoRA adapters fine-tuned to exhibit individual quirk behaviors (IDs 0-108, excluding 1, 21, 32, 54, 81, 84).

Llama-3.3-70B LoRA adapters from transcripts-contextual-optimism merged MOS experiment (zz0114).

Llama-3.3-70B LoRA adapters fine-tuned on benign behavior datasets (z1226).

Qwen3-14B meta-LoRA introspection adapters trained with varying number of samples (z1209).

Qwen3-14B LoRA adapters fine-tuned on heuristic behavior datasets (zz0104).