© 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. 38300
    Prev
    Next
    INDEX
    Explanations

    class, conda, ATOM, pulmonary

    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
    Negative Logits
    mÃŃ
    -0.10
    UBLIC
    -0.10
     Laud
    -0.09
    maid
    -0.09
    icut
    -0.08
    edException
    -0.08
     fictional
    -0.08
    hen
    -0.08
    ycl
    -0.08
    owing
    -0.08
    POSITIVE LOGITS
    SACTION
    0.11
    민êµŃ
    0.10
    atre
    0.10
    OfFile
    0.09
    adays
    0.09
    .GPIO
    0.09
    _WM
    0.09
    INCT
    0.08
     Fist
    0.08
    tempts
    0.08
    Activations Density 0.428%

    No Known Activations