© 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. 46403
    Prev
    Next
    INDEX
    Explanations

    two, three, four, numbers

    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
     Helen
    -0.09
     Nikola
    -0.09
     pairwise
    -0.09
    ussy
    -0.09
     multin
    -0.09
    à¹Īำ
    -0.08
     gover
    -0.08
     VÅ¡ech
    -0.08
     Martins
    -0.08
    isine
    -0.08
    POSITIVE LOGITS
    /th
    0.16
    ä¹ĭä¸Ģ
    0.15
    ãĢģä¸ī
    0.14
     birden
    0.14
    -One
    0.13
    ãĢģäºĮ
    0.12
    ged
    0.12
    -three
    0.12
    -two
    0.11
    /single
    0.11
    Activations Density 0.195%

    No Known Activations