© 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. 18521
    Prev
    Next
    INDEX
    Explanations

    US states

    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
     Canadian
    -0.13
    Canadian
    -0.13
     Winnipeg
    -0.10
     canada
    -0.10
    Americ
    -0.10
    èĨ
    -0.10
     Charlottesville
    -0.10
     canadian
    -0.09
     Albuquerque
    -0.09
     Canadians
    -0.09
    POSITIVE LOGITS
     California
    0.28
     Florida
    0.26
     Illinois
    0.25
     Pennsylvania
    0.25
     Massachusetts
    0.25
     Michigan
    0.24
     Texas
    0.23
     Maryland
    0.23
     Indiana
    0.23
    California
    0.22
    Activations Density 0.129%

    No Known Activations