© 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. 32471
    Prev
    Next
    INDEX
    Explanations

    Belgium postcode Lokeren

    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
     Bren
    -0.11
     Marseille
    -0.11
     Boh
    -0.10
     IMG
    -0.10
     Py
    -0.10
     Sor
    -0.09
     France
    -0.09
     ФоÑĢ
    -0.09
     Florian
    -0.09
     monot
    -0.09
    POSITIVE LOGITS
     Belgian
    0.39
     Belgium
    0.39
     Brussels
    0.35
     Belg
    0.33
     Flem
    0.31
     belg
    0.29
    .be
    0.27
     Gh
    0.24
    Bel
    0.22
    ussels
    0.19
    Activations Density 0.036%

    No Known Activations