© 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. 57347
    Prev
    Next
    INDEX
    Explanations

    function or variable names ending in (lst, (set, (arr

    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
    -0.09
     Agu
    -0.09
     Bust
    -0.09
    askell
    -0.09
     DataRow
    -0.09
    igon
    -0.08
    ulumi
    -0.08
    oram
    -0.08
     opposite
    -0.08
     AW
    -0.08
    POSITIVE LOGITS
     birinci
    0.16
     first
    0.15
    [first
    0.15
    çĶ²
    0.15
    两个
    0.14
    第ä¸Ģ
    0.14
     첫
    0.13
    (first
    0.13
    first
    0.13
     lhs
    0.13
    Activations Density 0.187%

    No Known Activations