© 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. 32798
    Prev
    Next
    INDEX
    Explanations

    killing, violence, harm

    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
     annihil
    -0.12
     Victims
    -0.09
     assail
    -0.09
     obl
    -0.09
    //}}
    -0.09
     horn
    -0.09
    ourn
    -0.09
     wreckage
    -0.09
    .toHexString
    -0.09
    ocht
    -0.09
    POSITIVE LOGITS
     kill
    0.42
     killing
    0.38
     kills
    0.35
    æĿĢ
    0.33
     killed
    0.31
    殺
    0.30
     Kill
    0.29
    kill
    0.29
    .kill
    0.27
    Kill
    0.26
    Activations Density 0.128%

    No Known Activations