We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.

I often see a lot of people with outdated understanding of modern LLMs.

This is probably the best interpretability research to date, by the leading interpretability research team.

It’s worth a read if you want a peek behind the curtain on modern models.

  • Womble@lemmy.worldEnglish
    0·
    6 months ago

    This is a really good science communication article, it describes their work in clear terms (finding structures that relate to abstract concepts, seeing when they are activated and how strengthening and weaking them modifies outputs) and goes into the implications for it. I’m probably going to save this link as a rebuttal for the people who claim LLMs just predict the next word and have no concepts embedded in them.

    • misk@sopuli.xyzEnglish
      0·
      6 months ago

      I doubt that anyone saying that LLM are calculating next word solely based on previous sequence. It’s still statistics, regardless of complexity.

      • Womble@lemmy.worldEnglish
        1·
        6 months ago

        Youd be surprised at the level of unthinking hatred around them, but even discarding that Ive seen it said often that LLMs have no internal model of what they are talking about as they are just next word generators. This quite clearly contradicts that interpretation.

      • Richard@lemmy.worldEnglish
        1·
        6 months ago

        Yes, but people forget that our brains, and therefore our minds, are also “simply” statistics, albeit very complex.