© 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. 57233
    Prev
    Next
    INDEX
    Explanations

    specifying conditions with "where"

    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
    .findIndex
    -0.09
    leck
    -0.09
    imore
    -0.08
     Hoe
    -0.08
    egan
    -0.08
    lin
    -0.08
    crawl
    -0.08
    æŃ¢
    -0.08
    eza
    -0.08
    errat
    -0.08
    POSITIVE LOGITS
     where
    0.36
    where
    0.30
     где
    0.28
     où
    0.26
    åħ¶ä¸Ń
    0.25
    ï¼Įåħ¶ä¸Ń
    0.25
     gdzie
    0.25
    (where
    0.24
     donde
    0.23
    \twhere
    0.23
    Activations Density 0.124%

    No Known Activations