© 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. 7898
    Prev
    Next
    INDEX
    Explanations

    city and town locations

    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
    Negative Logits
    IIIK
    -0.11
    adla
    -0.10
    íĨłíĨł
    -0.10
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.09
    innen
    -0.09
     Territory
    -0.09
    Intialized
    -0.09
    ecycle
    -0.09
    âĦĸâĦĸ
    -0.09
    @brief
    -0.09
    POSITIVE LOGITS
     town
    0.27
     city
    0.21
    city
    0.15
     fictional
    0.15
     cittÃł
    0.14
    fiction
    0.13
     cidade
    0.13
    åŁİå¸Ĥ
    0.13
    -town
    0.13
    town
    0.12
    Activations Density 0.218%

    No Known Activations