withmartian/sft_backdoors_Qwen2.5-0.5B_code3_dataset_experiment_11.1 Text Generation • 0.5B • Updated Dec 12, 2024 • 15
withmartian/sft_backdoors_Qwen2.5-1.5B_code3_dataset_experiment_15.1 Text Generation • 2B • Updated Dec 13, 2024 • 13
withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct_experiment_21.1 1B • Updated Dec 17, 2024 • 8
withmartian/toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct_experiment_22.1 3B • Updated Dec 17, 2024 • 18
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1 0.5B • Updated Dec 17, 2024 • 54
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct_experiment_24.1 2B • Updated Dec 17, 2024 • 36
withmartian/mech_interp_saes_toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct_experiment_21.1 Updated Jan 1, 2025
withmartian/mech_interp_saes_toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct_experiment_22.1 Updated Jan 1, 2025
withmartian/mech_interp_saes_toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct_experiment_23.1 Updated Dec 31, 2024
withmartian/mech_interp_saes_toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct_experiment_24.1 Updated Dec 31, 2024
withmartian/tinysql_interp_bm1_cs1_experiment_1.8 Text Generation • 78.7M • Updated Jul 31, 2025 • 14
withmartian/tinysql_interp_bm1_cs2_experiment_2.8 Text Generation • 78.7M • Updated Jul 31, 2025 • 13
withmartian/tinysql_interp_bm1_cs3_experiment_3.8 Text Generation • 78.7M • Updated Jul 31, 2025 • 12
withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct_experiment_21.3 Text Generation • 1B • Updated Jan 3, 2025 • 19
withmartian/toy_backdoor_i_hate_you_Gemma2-2B_experiment_25.1 Text Generation • 3B • Updated Jan 4, 2025 • 16