© 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. 53799
    Prev
    Next
    INDEX
    Explanations

    Perth and Western Australia places

    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
     Borough
    -0.12
    -0.11
     borough
    -0.11
     extr
    -0.10
     UM
    -0.10
     Suff
    -0.10
    ulton
    -0.09
     Tennessee
    -0.09
     Southampton
    -0.09
     Georgia
    -0.09
    POSITIVE LOGITS
     WA
    0.29
    WA
    0.25
     Perth
    0.23
     Frem
    0.22
     Western
    0.20
     Albany
    0.18
    PERT
    0.17
     Swan
    0.17
     Roe
    0.16
     Curt
    0.16
    Activations Density 0.031%

    No Known Activations