anchor
Findings
- IC-054Gemma 2 2B performance degrades substantially when routed through Gemma Scope SAEs, and SAE-based feature suppression causes broad cross-domain degradation rather than targeted knowledge removal [eval]
- IC-201Activating neuroticism-positive neurons in Llama-3-8B-Instruct causes the largest decline in general capabilities, while activating conscientiousness-positive neurons improves all benchmarks [eval]
- IC-395Most mainstream LLMs exhibit positive ADCE across five tasks, indicating reliance on deep structure for problem-solving, with ADCE strongly correlated with accuracy (r² > 0.7) [eval]
- IC-396Closed-source LLMs (GPT, Claude) rely more on deep structure than open-source LLMs (Llama, Mistral), and open-source models' surface sensitivity decreases with model scale [eval]
- IC-762GPT-4 and GPT-3.5 outperform humans in generation but underperform in discriminative (selective) evaluation across 10 of 13 language tasks [eval]
- IC-852Intrinsic self-correction without external feedback consistently degrades reasoning accuracy across GPT-3.5-turbo, GPT-4, GPT-4-turbo, and LLaMA-2-70B-chat [eval]
- IC-986Most LLMs lack tool usage awareness, with only ChatGPT exceeding 70% F1 in zero-shot evaluation [eval]