Sep 8, 2026 · cs.CLJ/K move · Enter open · S save
Raito Kiya, Satoki Ohashi, Kosuke Sato, Go Kamoda+5
1Tohoku University · 2SOKENDAI · 3NINJAL · 4MBZUAI · 5RIKEN
Large Language Models (LLMs) often exhibit "Attention Sink" (AS) and the accompanying "Massive Activations" (MAs) at the initial position of a sequence. These phenomena frequently co-occur, and MAs can pose challenges for low-bit quantization. In this study, we analyze the factors underlying AS and MAs that emerge at the initial position regardless of the token occupying it. Our experiments suggest that self-concentration of attention, resulting from the causal mask, and the subsequent Value-non-mixing in attention outputs contribute to AS and MAs. These findings provide new empirical evidence on the internal dynamics of LLMs, offering insights that may inform future quantization strategies and advance our understanding of the internal mechanisms of attention layers.