© 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. 64562
    Prev
    Next
    INDEX
    Explanations

    adding more comments or code qualities

    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
     moon
    -0.09
    çı
    -0.09
     signalling
    -0.09
     Wort
    -0.09
    .DataBind
    -0.09
     ÙħØ«
    -0.08
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.08
    recipe
    -0.08
    erialized
    -0.08
     Hawth
    -0.08
    POSITIVE LOGITS
     comments
    0.16
     dec
    0.15
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.15
     indent
    0.14
     commented
    0.14
     robust
    0.13
     commenting
    0.13
     documentation
    0.13
     COMMENTS
    0.13
    comments
    0.13
    Activations Density 0.185%

    No Known Activations