© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    city districts and exploration

    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
     towns
    -0.11
     hometown
    -0.11
     regional
    -0.10
    Regional
    -0.10
     Gotham
    -0.09
    reso
    -0.09
    åľ°æĸ¹
    -0.09
    TickCount
    -0.09
     Regional
    -0.09
     REGION
    -0.09
    POSITIVE LOGITS
     districts
    0.23
     CBD
    0.22
    CBD
    0.19
     downtown
    0.17
     central
    0.17
     cbd
    0.17
     district
    0.16
     Downtown
    0.15
     Cbd
    0.15
    owntown
    0.15
    Activations Density 0.158%

    No Known Activations