© 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. 18254
    Prev
    Next
    INDEX
    Explanations

    Southeast addresses and place names

    np_acts-logits-general · gemini-2.5-flash-lite

    Chinese addresses and location names, particularly in the Changzhou area.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     mosaic
    -0.11
     Hamp
    -0.10
    طاÙĦ
    -0.09
     Ying
    -0.09
    .Sin
    -0.09
     Wenger
    -0.09
     USB
    -0.09
     sequelize
    -0.09
     pec
    -0.08
     Jian
    -0.08
    POSITIVE LOGITS
     æ±Ł
    0.13
     Kent
    0.12
     Yale
    0.12
     Suz
    0.11
    æ±Ł
    0.11
     Jiang
    0.10
     Town
    0.10
     town
    0.10
    onet
    0.10
     Curt
    0.10
    Activations Density 0.069%

    No Known Activations