© 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. 34492
    Prev
    Next
    INDEX
    Explanations

    J words in addresses

    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
    obe
    -0.12
    ennie
    -0.11
    ane
    -0.11
    JM
    -0.11
    ames
    -0.10
    im
    -0.10
    enn
    -0.10
    ake
    -0.10
    ak
    -0.10
    он
    -0.09
    POSITIVE LOGITS
     oh
    0.12
    316
    0.11
    inding
    0.11
    icable
    0.11
    ustr
    0.11
    dling
    0.11
     ust
    0.11
     Edgar
    0.11
    y
    0.10
    iating
    0.10
    Activations Density 0.031%

    No Known Activations