© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 198
    Prev
    Next
    INDEX
    Explanations

    clauses starting with which

    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
    anko
    -0.12
     ìŀĪëĭ¤ê³ł
    -0.10
    .Then
    -0.10
    iaz
    -0.10
    ï¼ĮåĽłä¸º
    -0.09
    ìĿ¸ì§Ģ
    -0.09
     Sort
    -0.09
     Shan
    -0.09
     neboť
    -0.09
     Whats
    -0.09
    POSITIVE LOGITS
     which
    0.39
    which
    0.36
     což
    0.29
     WHICH
    0.29
     Which
    0.29
    Which
    0.28
     à¸ĭ
    0.24
     które
    0.21
    .which
    0.20
     коÑĤоÑĢое
    0.20
    Activations Density 0.171%

    No Known Activations