© 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. 64921
    Prev
    Next
    INDEX
    Explanations

    significant amounts

    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
    anon
    -0.11
    ulence
    -0.09
    krv
    -0.09
     conditions
    -0.09
    arker
    -0.09
    Isl
    -0.09
    peq
    -0.09
    ķĮ
    -0.08
    ottom
    -0.08
    NullOr
    -0.08
    POSITIVE LOGITS
     amount
    0.28
     amounts
    0.23
    amount
    0.22
     Amount
    0.18
    -sized
    0.17
     number
    0.16
     enough
    0.16
    Amount
    0.15
     sized
    0.15
    -scale
    0.14
    Activations Density 0.048%

    No Known Activations