© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35905
    Prev
    Next
    INDEX
    Explanations

    years following 191

    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
    tem
    -0.12
    ummer
    -0.11
    um
    -0.11
    ov
    -0.10
    o
    -0.10
    umm
    -0.10
    ''"
    -0.10
    craft
    -0.09
    etti
    -0.09
    ::::::::::::::::
    -0.09
    POSITIVE LOGITS
    st
    0.16
    ration
    0.12
    allas
    0.11
    stal
    0.11
    stk
    0.11
    inals
    0.10
    STALL
    0.10
    rapper
    0.09
    apolis
    0.09
    uring
    0.09
    Activations Density 0.017%

    No Known Activations