© 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. 28166
    Prev
    Next
    INDEX
    Explanations

    before you or we begin

    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
     be
    -0.15
    gether
    -0.12
    oret
    -0.10
    ogle
    -0.09
    ought
    -0.09
    iam
    -0.09
    -minded
    -0.09
     Fancy
    -0.09
     elabor
    -0.08
    ways
    -0.08
    POSITIVE LOGITS
    ’;re
    0.21
    're
    0.20
    've
    0.17
    ’;ve
    0.16
    'll
    0.15
    ’;ll
    0.14
     are
    0.13
    /we
    0.13
    eding
    0.12
    aned
    0.11
    Activations Density 0.123%

    No Known Activations