© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 9033
    Prev
    Next
    INDEX
    Explanations

    locations in Norway

    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
     eldre
    -0.22
     hvad
    -0.18
     noen
    -0.18
     danske
    -0.17
     godt
    -0.16
     hvordan
    -0.16
     dansk
    -0.14
     meget
    -0.14
     Baltic
    -0.14
     hvis
    -0.14
    POSITIVE LOGITS
     Norwegian
    0.31
     Norway
    0.31
     Oslo
    0.28
    Nor
    0.27
     Bergen
    0.26
     Nor
    0.23
     ноÑĢ
    0.23
    æĮ
    0.21
     NOR
    0.20
     nor
    0.19
    Activations Density 0.037%

    No Known Activations