Models and datasets for "Training Language Models To Explain Their Own Computations"
-
Transluce/features_explain_llama3.1_8b_simulator
8B • Updated • 48 -
Transluce/act_patch_llama_3.1_8b_counterfact
Viewer • Updated • 126k • 35 -
Transluce/input_ablation_qwen3_8b_mmlu_hint
Viewer • Updated • 14k • 27 • 1 -
Transluce/input_ablation_llama_3.1_8b_instruct_mmlu_hint
Viewer • Updated • 14k • 27