© 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. 7981
    Prev
    Next
    INDEX
    Explanations

    percentages for funds

    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
     equity
    -0.10
     KE
    -0.09
     stock
    -0.09
    _patch
    -0.09
     Stock
    -0.09
     Hoy
    -0.09
     Rut
    -0.09
    IBC
    -0.09
     Prest
    -0.09
     Cent
    -0.09
    POSITIVE LOGITS
     expense
    0.20
     Expense
    0.17
     fund
    0.17
     prospect
    0.17
    Expense
    0.16
     breakpoints
    0.15
     Morning
    0.15
     NAV
    0.15
    expense
    0.15
     Fund
    0.14
    Activations Density 0.021%

    No Known Activations