© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24791
    Prev
    Next
    INDEX
    Explanations

    city

    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
     Rural
    -0.15
     Counties
    -0.14
     rural
    -0.12
     villages
    -0.11
     provinc
    -0.09
     Vill
    -0.09
    itzer
    -0.09
     counties
    -0.09
    apor
    -0.09
     statewide
    -0.09
    POSITIVE LOGITS
     city
    0.82
    city
    0.59
     town
    0.52
    -city
    0.47
     cidade
    0.46
     cittÃł
    0.44
     City
    0.44
    (city
    0.43
    å¸Ĥ
    0.42
     гоÑĢод
    0.42
    Activations Density 0.147%

    No Known Activations