© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21678
    Prev
    Next
    INDEX
    Explanations

    proper code examples

    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
    tega
    -0.08
    éĺ³åŁİ
    -0.08
    kyt
    -0.07
    елÑĮно
    -0.07
     dol
    -0.07
     ÃľNÄ°VERS
    -0.07
     SolidColorBrush
    -0.07
     Lumpur
    -0.07
    idth
    -0.07
     ÏĦÎŃ
    -0.07
    POSITIVE LOGITS
     âĢĮ
    0.08
    anders
    0.07
    ,
    0.07
     altern
    0.07
    oyer
    0.07
    rippling
    0.07
     aliqua
    0.07
    \tRead
    0.07
     se
    0.07
    ocking
    0.07
    Activations Density 0.139%

    No Known Activations