© 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. 27653
    Prev
    Next
    INDEX
    Explanations

    well-known facts or concepts

    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
     alist
    -0.11
    447
    -0.11
    pon
    -0.10
    +-
    -0.09
     ì¢ħ
    -0.09
     Gad
    -0.09
    857
    -0.09
    PECT
    -0.09
     Dia
    -0.09
    ten
    -0.09
    POSITIVE LOGITS
    ledge
    0.21
    lege
    0.15
    ledged
    0.14
    s
    0.13
     facts
    0.13
     quantities
    0.11
    _hosts
    0.11
     fact
    0.11
    æĤī
    0.11
     faces
    0.11
    Activations Density 0.045%

    No Known Activations