© 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. 10749
    Prev
    Next
    INDEX
    Explanations

    phrases with "as" and pronouns

    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
     follando
    -0.09
    actionDate
    -0.09
    èĨľ
    -0.09
     Quickly
    -0.09
    odÃŃ
    -0.09
     باÙĤ
    -0.08
     kontakte
    -0.08
    447
    -0.08
     nuest
    -0.08
    vice
    -0.08
    POSITIVE LOGITS
     suddenly
    0.13
    ãģĻãĤĭãģ¨
    0.10
    while
    0.10
     sudden
    0.10
    oin
    0.10
     thoughts
    0.10
     Legend
    0.09
     вдÑĢÑĥг
    0.09
    λÏĮ
    0.09
     Ment
    0.09
    Activations Density 0.077%

    No Known Activations