© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10459
    Prev
    Next
    INDEX
    Explanations

    gib mir das

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

    polite requests or instructions, particularly those asking for information or action to be provided.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     your
    -0.14
     seu
    -0.11
    ä½łçļĦ
    -0.11
     his
    -0.10
     a
    -0.10
     à¤ħपन
    -0.10
    your
    -0.10
     prob
    -0.09
    -your
    -0.09
     Ñģвоего
    -0.09
    POSITIVE LOGITS
     the
    0.12
    ¿ÃĤ
    0.10
    <|begin_of_text|>
    0.10
     VÅ¡ech
    0.09
     iddi
    0.09
     tÄĽch
    0.09
     -*-č\n
    0.09
    ÂĢÂĢ
    0.09
    ERRU
    0.08
     chtÄĽ
    0.08
    Activations Density 0.113%

    No Known Activations