© 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. 34476
    Prev
    Next
    INDEX
    Explanations

    anti- followed by words

    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
    ous
    -0.10
    outers
    -0.10
    anko
    -0.09
    /dr
    -0.09
    LY
    -0.09
    esh
    -0.09
    curity
    -0.09
    ÑĩеÑģкое
    -0.09
    manent
    -0.09
     ãĦ
    -0.08
    POSITIVE LOGITS
    à¸Ĺาà¸Ļ
    0.16
    ForgeryToken
    0.14
    uated
    0.13
    aging
    0.13
    Gravity
    0.12
    icrobial
    0.12
    heroes
    0.12
     gravity
    0.12
     aging
    0.12
    ipated
    0.11
    Activations Density 0.015%

    No Known Activations