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_addition_gemma-2-9b-it1-layer-addition-v2Binary-Addition-LLM-POC1-layer-additioncheckpoints_cls_latentqa_only_addition_Qwen3-8Bcheckpoints_latentqa_only_addition_Qwen3-8Bcheckpoints_cls_only_addition_Qwen3-8Bpythia-410m-addition-first-ftcheckpoints_latentqa_only_addition_gemma-2-9b-itcheckpoints_cls_latentqa_sae_addition_Qwen3-8Bcheckpoints_cls_only_addition_gemma-2-9b-itpythia-6.9b-addition-first-ftcheckpoints_cls_latentqa_only_addition_gemma-2-9b-itpythia-1.4b-addition-first-ftpythia-2.8b-addition-first-ftpythia-1b-addition-first-ftMistral-7B-v0.1-addition-first-ftLlama-2-7b-hf-addition-first-ftconvergent-llama-300M-muon-addition_3digitMistral-7B-v0.1-addition-random-standardized-random-namesMistral-7B-v0.1-addition-random-standardized-many-random-namesaddition_modeladdition-modeladditional_models_Qwen_Qwen1.5-0.5B-Chat_minimality-mmd_defence_steps_10000convergent-llama-300M-adamw-additionconvergent-llama-300M-muon-6digit-addition_6digit_llamagpt2_finetuned_addition_arithmetic_10_100_hash_nsablation_additional_minimality-mmd_defence_steps_1000convergent-llama-300M-muon-addition_hex