© 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. 16994
    Prev
    Next
    INDEX
    Explanations

    PyQt5 imports

    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
     QPainter
    -0.11
    InputDialog
    -0.11
    ScrollPane
    -0.10
    ipmap
    -0.10
     lik
    -0.09
     Lik
    -0.09
    TabControl
    -0.09
     Sung
    -0.08
    QB
    -0.08
    vos
    -0.08
    POSITIVE LOGITS
     Q
    0.17
    Q
    0.12
    INESS
    0.09
     Busy
    0.09
    'gc
    0.09
    ÅĻÃŃt
    0.09
    mdi
    0.09
    ForRow
    0.09
     Slot
    0.09
    Busy
    0.09
    Activations Density 0.013%

    No Known Activations