© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    comma followed by 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
    658
    -0.09
    é®
    -0.09
     Sort
    -0.09
    :animated
    -0.08
    //{{
    -0.08
     unh
    -0.08
    enet
    -0.08
    ridge
    -0.08
    ribly
    -0.08
    ãĥªãĥ¼
    -0.08
    POSITIVE LOGITS
     which
    0.36
    which
    0.34
    Which
    0.25
     WHICH
    0.24
     Which
    0.24
     což
    0.22
     коÑĤоÑĢÑĭй
    0.20
     коÑĤоÑĢаÑı
    0.19
     które
    0.18
     коÑĤоÑĢое
    0.17
    Activations Density 0.066%

    No Known Activations