© 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. 46138
    Prev
    Next
    INDEX
    Explanations

    describing behavior

    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
    Negative Logits
    Unnamed
    -0.09
    ahn
    -0.09
    bourg
    -0.09
    lexer
    -0.08
    ľ
    -0.08
    iyan
    -0.08
    avra
    -0.08
    icked
    -0.08
    XL
    -0.08
    /script
    -0.08
    POSITIVE LOGITS
     litter
    0.12
     Trash
    0.11
    /help
    0.11
     helping
    0.11
    iar
    0.10
     help
    0.10
     someone
    0.10
     seat
    0.10
     nett
    0.09
    浪
    0.09
    Activations Density 0.007%

    No Known Activations