# @DavidDAfrica — 2026-08-25

♥6 ↻0 · https://x.com/DavidDAfrica/status/2092299516288643438

We then combine these measures into a single score, and evaluate a wide variety of open models.

Surprisingly, we find that Llama 3.1 8B Instruct performs best, even over larger and more modern models (such as GLM 5.2, or Llama 4 400B). Both GPT-OSS models were not very good at controlling their activations.

These measurements suggest that activation controllability may be difficult to infer from a model’s size or capability index, and must be measured directly.

![photo](../../../media/HQlXUmxbQAITLdP.jpg)
tags: author:daviddafrica, has-image, kind:image, kind:tweet, on:glm-5-2, year:2026
cited on: _dossiers/glm-5-2.md, glm-5-2