© 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. 61234
    Prev
    Next
    INDEX
    Explanations

    map, file, series, loop, end

    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
    merican
    -0.15
    anguage
    -0.13
    icense
    -0.13
    mith
    -0.13
    -
    -0.13
    acific
    -0.12
    resident
    -0.12
    obile
    -0.11
    olume
    -0.11
    oice
    -0.11
    POSITIVE LOGITS
    /-
    0.32
    ftware
    0.18
    entication
    0.16
    raries
    0.15
    gether
    0.14
    CLUDE
    0.14
    acters
    0.14
    ern
    0.13
    imum
    0.13
    ysics
    0.12
    Activations Density 0.328%

    No Known Activations