© 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. 10744
    Prev
    Next
    INDEX
    Explanations

    always verb

    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
    oin
    -0.12
    Æł
    -0.09
    emez
    -0.09
     samot
    -0.09
    elp
    -0.09
    erva
    -0.08
    ä¸Ī
    -0.08
    acles
    -0.08
    _flutter
    -0.08
     Gott
    -0.08
    POSITIVE LOGITS
    cky
    0.12
     reply
    0.12
     ending
    0.10
     refer
    0.10
     replied
    0.10
     (?)
    0.10
     default
    0.10
     start
    0.10
    -al
    0.10
     err
    0.09
    Activations Density 0.032%

    No Known Activations