© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61827
    Prev
    Next
    INDEX
    Explanations

    law and legal regulation

    np_acts-logits-general · gemini-2.5-flash-lite

    formal legal or governmental text, especially references to laws, regulations, codes, and jurisdictions, often appearing in headings or summary/overview phrasing.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assertions
    -0.11
     генеÑĢа
    -0.10
    įng
    -0.10
     mandated
    -0.09
     -*-č\n
    -0.09
    è£
    -0.09
     меÑĤалли
    -0.09
     Pazar
    -0.09
    ¶Į
    -0.09
     Mandatory
    -0.08
    POSITIVE LOGITS
     law
    0.27
     Law
    0.22
     laws
    0.21
     legislation
    0.19
    æ³ķ
    0.18
    law
    0.16
    -law
    0.16
     ÙĤاÙĨÙĪÙĨ
    0.16
    Law
    0.16
     Act
    0.16
    Activations Density 0.315%

    No Known Activations