© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    pending or outstanding invoices

    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
     uninterrupted
    -0.09
     mute
    -0.09
     accr
    -0.09
     tÆ°á»Ľng
    -0.09
    ÌĤ
    -0.08
     uncont
    -0.08
     Hidden
    -0.08
    uch
    -0.08
     Preserve
    -0.08
     vô
    -0.08
    POSITIVE LOGITS
     outstanding
    0.69
     Outstanding
    0.52
     pending
    0.47
     pend
    0.41
     Pend
    0.39
    pending
    0.37
     Pending
    0.35
    pend
    0.35
    Pending
    0.34
    .pending
    0.32
    Activations Density 0.215%

    No Known Activations