© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    information booth reception

    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
     waitress
    -0.10
     Alle
    -0.09
    ardown
    -0.09
     aisle
    -0.09
    _portal
    -0.09
     sÃŃd
    -0.09
     Regional
    -0.09
    Hierarchy
    -0.09
    ograd
    -0.09
    /browse
    -0.09
    POSITIVE LOGITS
     counter
    0.29
     desk
    0.27
     reception
    0.26
     Desk
    0.22
    counter
    0.22
    desk
    0.21
     Reception
    0.21
     Counter
    0.21
    Desk
    0.20
     conc
    0.19
    Activations Density 0.127%

    No Known Activations