© 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. 40368
    Prev
    Next
    INDEX
    Explanations

    , even though or through

    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
     prey
    -0.12
    ajs
    -0.11
     soul
    -0.10
     Soul
    -0.10
    akin
    -0.10
     Matte
    -0.09
    iska
    -0.09
    inci
    -0.09
     ong
    -0.09
     Levin
    -0.09
    POSITIVE LOGITS
    Grace
    0.11
    æģ©
    0.11
     Jesus
    0.10
     undes
    0.10
     suff
    0.10
    à¸Ĺà¸ĺ
    0.10
     Horton
    0.10
     grace
    0.10
    (gr
    0.10
     Grace
    0.10
    Activations Density 0.015%

    No Known Activations