© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22404
    Prev
    Next
    INDEX
    Explanations

    factually consistent

    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
     ÑĩиÑģлÑĸ
    -0.08
    ãĢĤwww
    -0.07
    ;amp
    -0.07
    ÅĻád
    -0.07
    /by
    -0.07
    \xc
    -0.07
    ÅĻÃŃz
    -0.07
     %[
    -0.06
    institution
    -0.06
    Å®
    -0.06
    POSITIVE LOGITS
     Gur
    0.08
    &apos
    0.07
     завиÑģим
    0.07
    unbind
    0.07
     aforementioned
    0.07
    inel
    0.07
    reh
    0.07
    .ObjectId
    0.07
    Unhandled
    0.07
    dirname
    0.06
    Activations Density 2.287%

    No Known Activations