© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35405
    Prev
    Next
    INDEX
    Explanations

    cities following "in"

    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
     Gujarat
    -0.10
     Anadolu
    -0.10
     Lanka
    -0.10
     Rajasthan
    -0.10
    lez
    -0.10
    ＿＿＿＿＿＿＿＿
    -0.09
     Karnataka
    -0.09
     Greenwich
    -0.09
     Maharashtra
    -0.09
     Mayo
    -0.09
    POSITIVE LOGITS
     London
    0.23
     تÙĩراÙĨ
    0.19
    London
    0.18
     ÐľÐ¾Ñģк
    0.18
     Los
    0.16
     Paris
    0.16
    åĮĹ京
    0.15
     Toronto
    0.15
     ìĦľìļ¸
    0.15
     Atlanta
    0.14
    Activations Density 0.227%

    No Known Activations