© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38333
    Prev
    Next
    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of dates or date-related phrases (e.g., years, months, "current date", "knowledge cutoff").

    oai_token-act-pair · gpt-5-mini
    Triggered by @yooniel31

    The neuron is detecting numeric tokens and punctuation used in dates (e.g. year, month, day numbers and their separators).

    oai_token-act-pair · o4-mini
    Triggered by @yooniel31
    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
    Negative Logits
    4
    -0.09
    2
    -0.09
     Hod
    -0.09
     Landing
    -0.09
    0
    -0.09
     Lor
    -0.08
    92
    -0.08
    255
    -0.08
    3
    -0.08
     Morr
    -0.08
    POSITIVE LOGITS
    âĸłâĸł
    0.11
    пÑĢимеÑĢ
    0.09
    toa
    0.09
     Schultz
    0.09
    .UserInfo
    0.09
    ccess
    0.09
    ellers
    0.08
     Cassidy
    0.08
    ynet
    0.08
     Chat
    0.08
    Activations Density 0.012%

    No Known Activations