© 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. 45047
    Prev
    Next
    INDEX
    Explanations

    ifs de, training and, instruments and

    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
    .wx
    -0.07
    .mybatis
    -0.07
    .mybatisplus
    -0.07
    _registro
    -0.06
     naken
    -0.06
     sạn
    -0.06
    `]
    -0.06
    .Dto
    -0.06
    anlar
    -0.06
     Sez
    -0.06
    POSITIVE LOGITS
     \`
    0.09
     _______,
    0.08
     BÄ°L
    0.07
     âĹij
    0.07
    -âĢIJ
    0.07
    .asInstanceOf
    0.07
    ï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ı
    0.07
    дап
    0.07
    าà¸ļาล
    0.06
    [,]
    0.06
    Activations Density 0.173%

    No Known Activations