© 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. 64586
    Prev
    Next
    INDEX
    Explanations

    politely decline

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     restraint
    -0.10
    ÃĹ\n\n
    -0.10
     withheld
    -0.10
     repealed
    -0.09
     abolished
    -0.09
     Intro
    -0.09
    ¥
    -0.09
     restraining
    -0.09
    advanced
    -0.09
     ench
    -0.09
    POSITIVE LOGITS
     block
    0.16
     decline
    0.16
     flag
    0.14
     declining
    0.14
     refuse
    0.14
     declined
    0.13
    _flag
    0.13
     Reported
    0.13
     Flag
    0.13
    flag
    0.13
    Activations Density 0.101%

    No Known Activations