© 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. 27463
    Prev
    Next
    INDEX
    Explanations

    numerical data or resource

    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
    o
    -0.10
    ersh
    -0.10
     Samar
    -0.10
    åĭ¤
    -0.10
     incumb
    -0.09
    v
    -0.09
    b
    -0.09
    y
    -0.08
     tou
    -0.08
     Kab
    -0.08
    POSITIVE LOGITS
    arrass
    0.11
    Č
    0.09
     Courtesy
    0.09
    BUR
    0.09
     Barg
    0.09
    lant
    0.09
    pon
    0.09
     Belediye
    0.09
    .sig
    0.09
     Prayer
    0.09
    Activations Density 0.007%

    No Known Activations