如果你在做ICL样本选择或主动学习，这篇论文用实验告诉你MLP激活值这条路走不通，省下试错时间。做LLM推理效率或特征分析的开发者，看完会理解为什么SAE可能是更好的方向。
该论文系统检验了基于MLP激活值的深度主动学习方法在LLM上下文学习（ICL）样本选择中的有效性。研究者使用Llama-3.2-3B和Qwen2.5-3B模型，在分类和生成任务上测试了多种注意力掩码策略，发现MLP输出的激活值（包括大规模激活和前四阶矩）与样本质量或任务性能的Spearman相关系数最高仅0.33，表明该方法不可靠。论文推测失败原因可能是“叠加”现象（模型表示的特征数超过维度数），并指出稀疏自编码器（SAE）可能是未来方向。这是目前最全面的MLP激活值主动学习在ICL中的分析，但结论为负。
Activation-Based Active Learning for In-Context Learning: Challenges and Insights
Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples. We present the most comprehensive analysis to date of MLP activation-based deep active learning methods applied to in-context learning, including how different attention masking strategies impact active learning across diverse classification and generative datasets, using both Llama-3.2-3B and Qwen2.5-3B base models. However, we find a negative result: MLP outputs, viewed through the lenses of massive activations or the first four moments, do not correlate with example quality or task performance. Specifically, the absolute Spearman correlation coefficient is at most 0.33 for all tasks and models we tested, showing that such activation-based sampling should not be used for in-context learning. We hypothesise that this may be due to superposition, whereby models represent more features than they have dimensionality, suggesting that methods like Sparse Autoencoders (SAEs) may be a promising future direction.