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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44438
    Prev
    Next
    INDEX
    Explanations

    urban planning 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
    Not in Any Lists

    No Comments

    Negative Logits
    Province
    -0.11
     provinc
    -0.10
     province
    -0.10
    aeper
    -0.10
    province
    -0.10
     Province
    -0.09
    éļª
    -0.09
    adena
    -0.09
     provinces
    -0.08
    éĻ©
    -0.08
    POSITIVE LOGITS
     urban
    0.35
     Urban
    0.29
    urban
    0.27
    Urban
    0.26
     planning
    0.23
     Planning
    0.22
     cities
    0.22
     urb
    0.22
     city
    0.22
    åŁİå¸Ĥ
    0.20
    Activations Density 0.077%

    No Known Activations