© 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. 53590
    Prev
    Next
    INDEX
    Explanations

    brazilian president, stocks, football

    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
     spanish
    -0.15
     Tus
    -0.14
     Españ
    -0.13
     Spanish
    -0.13
     MarÃŃa
    -0.12
    Spanish
    -0.12
     nuest
    -0.12
     Herrera
    -0.11
     Spain
    -0.11
     España
    -0.11
    POSITIVE LOGITS
     Brazil
    0.34
     Brazilian
    0.31
    Brazil
    0.29
     Brasil
    0.24
     brasile
    0.23
     Bras
    0.21
     Amazon
    0.21
     Guar
    0.21
    razil
    0.20
     Osw
    0.19
    Activations Density 0.197%

    No Known Activations