models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
checkpoints_latentqa_cls_past_lens_addition_Qwen3-8Bcheckpoints_latentqa_cls_past_lens_Qwen3-14Brecipe-lens-4bcheckpoints_latentqa_cls_past_lens_Llama-3_1-8B-Instructcheckpoints_latentqa_cls_past_lens_addition_gemma-2-9b-itcheckpoints_cls_latentqa_past_lens_Qwen3-1_7Bcheckpoints_latentqa_cls_past_lens_Qwen3-4Bcheckpoints_cls_latentqa_past_lens_Qwen3-32Bcheckpoints_latentqa_cls_past_lens_gemma-3-27b-itcheckpoints_cls_latentqa_past_lens_400k_Qwen3-8Bcheckpoints_cls_latentqa_sae_past_lens_Qwen3-8Bcheckpoints_latentqa_cls_past_lens_gemma-2-27b-itcheckpoints_Qwen3-8B_past_lens_only_500kadam-reupload-qwen3-8b-latentqa-cls-past-lenscheckpoints_cls_latentqa_past_lens_Llama-3_2-1B-InstructText-Scrutiny-LLMcheckpoints_cls_latentqa_past_lens_gemma-3-1b-itmodulation-lens-4bullet-rl-step50lens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_6_3e-5_1kcheckpoints_codex_old_past_lens_300k_full_mix_plus_synthetic_qa_v3modulation-lens-grid-C-raw-meansublens-loss-minimality_lr_2e-5_attack_meta-llama_Llama-2-7b-chat-hf_1_num_layers_32_8e-5_10kcheckpoints_Qwen3-8B_full_mix_500k_past_lens_synthetic_qa_v3_replace_lqamodulation-lens-grid-B-jspace-nomeansubmodulation-lens-grid-D-raw-nomeansubmodulation-lens-grid-A-jspace-meansubcheckpoints_latentqa_cls_past_lens_gemma-2-9b-it_lr_1e-6checkpoints_latentqa_cls_past_lens_gemma-2-9b-it_lr_1e-4cot-oracle-paper-ablation-ours-3layers-onpolicy-lens-onlycheckpoints_latentqa_cls_past_lens_gemma-3-4b-it