© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    weekend and Saturday plans

    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
    Negative Logits
     Mondays
    -0.21
     mornings
    -0.20
     Tues
    -0.19
     Nights
    -0.13
     daily
    -0.12
     christmas
    -0.12
     nights
    -0.12
     Thurs
    -0.12
     Christmas
    -0.11
     Tue
    -0.11
    POSITIVE LOGITS
     weekend
    0.84
     Weekend
    0.64
     weekends
    0.53
     Saturday
    0.35
    Saturday
    0.31
    week
    0.29
    Week
    0.26
     Wochen
    0.25
     вÑĭÑħод
    0.23
    -week
    0.23
    Activations Density 0.140%

    No Known Activations