© 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. 18706
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    à¸ģรม
    -0.10
     Frances
    -0.09
    ,default
    -0.09
    ãĤīãģĽ
    -0.08
    rott
    -0.08
    onn
    -0.08
    descricao
    -0.08
    æ±
    -0.08
    Insensitive
    -0.08
    nist
    -0.08
    POSITIVE LOGITS
     name
    0.28
    name
    0.21
     Name
    0.19
    Name
    0.18
    _name
    0.17
    ĵåIJį
    0.17
    .name
    0.16
     signature
    0.16
    \tname
    0.16
     имÑı
    0.15
    Activations Density 0.092%

    No Known Activations