© 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. 5692
    Prev
    Next
    INDEX
    Explanations

    foreign countries and cities

    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
     utrecht
    -0.10
     belg
    -0.09
     rotterdam
    -0.09
     Ùģارس
    -0.09
     Belize
    -0.09
     jenter
    -0.09
    evi
    -0.09
    retch
    -0.08
    .Undef
    -0.08
    gsub
    -0.08
    POSITIVE LOGITS
     abroad
    0.19
     England
    0.19
     Europe
    0.18
     London
    0.17
     Germany
    0.16
     Australia
    0.15
     France
    0.15
     California
    0.15
     Canada
    0.15
     States
    0.14
    Activations Density 0.162%

    No Known Activations