© 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. 63684
    Prev
    Next
    INDEX
    Explanations

    major cities and urban areas

    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
     locality
    -0.09
    itch
    -0.09
     suburban
    -0.09
     suburb
    -0.08
     Bryant
    -0.08
     slim
    -0.08
     Province
    -0.08
     mogul
    -0.08
     affluent
    -0.08
    DRV
    -0.08
    POSITIVE LOGITS
     cities
    0.53
     major
    0.42
     Cities
    0.40
    cities
    0.38
    Cities
    0.35
    åŁİå¸Ĥ
    0.31
     towns
    0.30
     city
    0.29
    major
    0.29
     urban
    0.29
    Activations Density 0.119%

    No Known Activations