© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37864
    Prev
    Next
    INDEX
    Explanations

    time duration or frequency

    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
     Timeline
    -0.20
    Timeline
    -0.17
     Timothy
    -0.17
     Timing
    -0.17
     TIM
    -0.17
    TIM
    -0.15
     Tim
    -0.15
    _TIM
    -0.15
    _timeline
    -0.14
    Tim
    -0.14
    POSITIVE LOGITS
     time
    0.99
    time
    0.65
    æŶéĹ´
    0.62
    \ttime
    0.54
    æĻĤéĸĵ
    0.54
    (time
    0.54
    .time
    0.53
     вÑĢемÑı
    0.51
     вÑĢемени
    0.50
     tiempo
    0.50
    Activations Density 0.161%

    No Known Activations