Detection-model andyrdt/saes-llama-3.1-8b-instruct Updated May 21, 2025 • 6 MLP-SAE/qwen2.5-32b-sae Updated Feb 14 MLP-SAE/Qwen2.5-14B-Instruct-bias-sft Updated Mar 9 MLP-SAE/Llama-3.1-8B-Instruct-bias-sft Updated Mar 9
Detection-data MLP-SAE/Qwen2.5-14B-Instruct-code-evol Viewer • Updated Mar 8 • 842k • 7 MLP-SAE/Qwen2.5-32B-Instruct-code-evol Viewer • Updated Mar 4 • 1.06M • 9 MLP-SAE/Llama-3.1-8B-Instruct-code-evol Viewer • Updated Mar 7 • 759k • 8 MLP-SAE/OLMo-3-7B-code-evol Viewer • Updated Mar 4 • 193k • 8
Detection-model andyrdt/saes-llama-3.1-8b-instruct Updated May 21, 2025 • 6 MLP-SAE/qwen2.5-32b-sae Updated Feb 14 MLP-SAE/Qwen2.5-14B-Instruct-bias-sft Updated Mar 9 MLP-SAE/Llama-3.1-8B-Instruct-bias-sft Updated Mar 9
Detection-data MLP-SAE/Qwen2.5-14B-Instruct-code-evol Viewer • Updated Mar 8 • 842k • 7 MLP-SAE/Qwen2.5-32B-Instruct-code-evol Viewer • Updated Mar 4 • 1.06M • 9 MLP-SAE/Llama-3.1-8B-Instruct-code-evol Viewer • Updated Mar 7 • 759k • 8 MLP-SAE/OLMo-3-7B-code-evol Viewer • Updated Mar 4 • 193k • 8