© 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. 4504
    Prev
    Next
    INDEX
    Explanations

    trade and commerce

    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
     purchasers
    -0.09
     embassy
    -0.09
    IRM
    -0.09
     íıīëĭ¹
    -0.09
     Wholesale
    -0.08
    irma
    -0.08
    ког
    -0.08
     اÙĦصÙĨ
    -0.08
    ritz
    -0.08
     Blur
    -0.08
    POSITIVE LOGITS
     trade
    0.65
    trade
    0.47
     trading
    0.45
     Trade
    0.44
     trades
    0.39
    -trade
    0.39
     traded
    0.39
    Trade
    0.39
    è´¸
    0.38
     commerce
    0.37
    Activations Density 0.113%

    No Known Activations