Kentaro Inui, Hinrich Schütze, Hilal AlQuabeh, Sebastian Gerstner
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We analyze the learned input-output behavior of GLU-based neurons in large language models (LLMs). We propose a simple analysis method: For each neuron, we compute the cosine similarities between its input (reading) and output (writing) weight vectors. In this scheme, a strong negative cosine similarity indicates the neuron weakens the direction it detects in the residual stream, so we call this a weakening neuron. This allows us to gain a number of novel insights. First, we show that nine different LLMs have similar patterns: weakening neurons appear mostly in late layers whereas their counterparts, (conditional) strengthening neurons, are frequent in early-middle layers. Second, we find that weakening neurons display surprising behavior: even though there are few, they activate often and have a large influence on model behavior. Third, weakening neurons have a strong effect on model output when gate values are negative -- which is surprising since negative gate values are not expected to encode functionality.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2609.18612")
get_code_for_paper("2609.18612")
have("2609.18612")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2609.18612.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2609.18612)
Connect an agent — have() is free.