© 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. 46627
    Prev
    Next
    INDEX
    Explanations

    store and the following word

    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
     sebuah
    -0.18
    ä¸Ģ个
    -0.17
     má»Ļt
    -0.14
     nÃły
    -0.13
    ä¸ĢåĢĭ
    -0.13
     eine
    -0.13
     een
    -0.12
    æŁIJ
    -0.12
    ä¸Ģç§į
    -0.12
    these
    -0.11
    POSITIVE LOGITS
     the
    0.20
    the
    0.10
    istrovstvÃŃ
    0.09
    -lnd
    0.09
    ,the
    0.08
    .)\n\n\n\n
    0.08
     migrationBuilder
    0.08
    \tthe
    0.08
    GuidId
    0.07
     chtÄĽ
    0.07
    Activations Density 0.183%

    No Known Activations