© 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. 10102
    Prev
    Next
    INDEX
    Explanations

    Chicago and its famous associations

    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
     NY
    -0.10
     NZ
    -0.10
     nz
    -0.10
     Reeves
    -0.10
     chatt
    -0.09
     Nass
    -0.09
    NZ
    -0.09
     Cypress
    -0.09
     hills
    -0.08
    جة
    -0.08
    POSITIVE LOGITS
     Chicago
    0.68
    Chicago
    0.61
     Illinois
    0.55
     chicago
    0.52
    icago
    0.41
     Blackhawks
    0.37
     Cubs
    0.36
    èĬĿ
    0.33
    Ill
    0.32
     IL
    0.27
    Activations Density 0.029%

    No Known Activations