© 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. 46263
    Prev
    Next
    INDEX
    Explanations

    these are stationary devices that

    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
    ¦æĥħ
    -0.09
     -*-č\n
    -0.08
    .Formatter
    -0.08
    yne
    -0.08
    âĦĸâĦĸ
    -0.08
    ardu
    -0.08
    entifier
    -0.08
    <|begin_of_text|>
    -0.08
    lak
    -0.07
    conds
    -0.07
    POSITIVE LOGITS
     conventional
    0.10
     larger
    0.09
     typically
    0.08
     mainstream
    0.08
     wr
    0.08
    .www
    0.08
     throughout
    0.08
     Slo
    0.08
     common
    0.07
     generally
    0.07
    Activations Density 0.057%

    No Known Activations