© 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. 59805
    Prev
    Next
    INDEX
    Explanations

    for a moment

    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
     Tomorrow
    -0.09
     Sala
    -0.09
    oute
    -0.09
    Tomorrow
    -0.09
     forthcoming
    -0.09
    apan
    -0.09
     Recently
    -0.09
    .learning
    -0.09
    Recent
    -0.09
     kür
    -0.09
    POSITIVE LOGITS
     пока
    0.38
     right
    0.30
    缮åīį
    0.30
    æļĤ
    0.29
     zatÃŃm
    0.29
     until
    0.28
     moment
    0.26
     initially
    0.24
     ÑģейÑĩаÑģ
    0.23
    until
    0.23
    Activations Density 0.180%

    No Known Activations