© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 60068
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Robbins
    -0.11
    APO
    -0.10
    undry
    -0.10
    ResourceId
    -0.09
     Sark
    -0.09
     sund
    -0.09
    ISBN
    -0.09
    _EPS
    -0.09
     unh
    -0.09
    kup
    -0.09
    POSITIVE LOGITS
    pp
    0.18
     pp
    0.17
     pages
    0.16
     pá
    0.12
    \tpp
    0.11
     Pages
    0.11
    .pages
    0.11
    pages
    0.11
    ê¶Į
    0.10
     Article
    0.10
    Activations Density 0.008%

    No Known Activations