arXiv:2509.22166v2 Announce Type: replace-cross Abstract: The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N:M) pruning is well-established for weights, its application to activation pruning remains underexplored despite its potential for dynamic, input-adaptive compression and reductions in I/O overhead. This work presents a comprehensive analysis of methods for post-training N:M activation pruning in LLMs. Across multiple LLMs, we demonstrate that pruning activations enables superior preservation of generative capabilities compared to weight pruning at equivalent sparsity levels. We evaluate lightweight, plug-and-play error mitigation techniques and pruning criteria, establishing strong hardware-friendly baselines that require minimal calibration. Furthermore, we explore sparsity patterns beyond NVIDIA's standard 2:4, showing that the 16:32 pattern achieves performance nearly on par with unstructured sparsity. However, considering the trade-off between flexibility and hardware implementation complexity, we focus on the 8:16 pattern as a superior candidate. Our findings provide both effective practical methods for activation pruning and a motivation for future hardware to support more flexible sparsity patterns. Our code is available https://anonymous.4open.science/r/Structured-Sparse-Activations-Inference-EC3C/README.md .

arXiv:2509.22067v2 Announce Type: replace-cross Abstract: Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially safer alternative to fine-tuning. We demonstrate the opposite: steering systematically breaks model alignment safeguards, making it comply with harmful requests. Through extensive experiments on different model families, we show that even steering in a random direction can increase the probability of harmful compliance from 0% to 1-13%. Alarmingly, steering benign features from a sparse autoencoder (SAE), a common source of interpretable directions, demonstrates a comparable harmful potential. Finally, we show that combining 20 randomly sampled vectors that jailbreak a single prompt creates a universal attack, significantly increasing harmful compliance on unseen requests. These results challenge the paradigm of safety through interpretability, showing that precise control over model internals does not guarantee precise control over model behavior.