© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 61007
    Prev
    Next
    INDEX
    Explanations

    Specifically

    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
    ä¹Łæľī
    -0.13
     ayrıca
    -0.12
     Ayrıca
    -0.12
     też
    -0.11
     also
    -0.11
    .plus
    -0.11
     juga
    -0.11
    à¸Ńà¸ģà¸Īาà¸ģà¸Ļ
    -0.11
     ÑĤакже
    -0.11
    Also
    -0.10
    POSITIVE LOGITS
    æ¯ķ
    0.14
    ä¾ĭå¦Ĥ
    0.12
     Specifically
    0.12
     Nam
    0.12
     many
    0.11
     Because
    0.11
     Many
    0.11
    Indeed
    0.11
     Trad
    0.11
    Nam
    0.10
    Activations Density 0.042%

    No Known Activations