© 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. 41025
    Prev
    Next
    INDEX
    Explanations

    mind that, between civil, utilizes conditional

    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
    instanc
    -0.08
    GNUC
    -0.07
    ynchronously
    -0.07
     noqa
    -0.07
     Mills
    -0.07
    /***/
    -0.07
     Swe
    -0.07
     uncert
    -0.07
     nextProps
    -0.06
    ing
    -0.06
    POSITIVE LOGITS
    URLException
    0.09
    įng
    0.09
    EMPLARY
    0.08
    lantı
    0.08
    owitz
    0.08
    roys
    0.08
    TouchUpInside
    0.07
    memberof
    0.07
     afore
    0.07
    .MoveNext
    0.07
    Activations Density 1.364%

    No Known Activations