© 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. 36698
    Prev
    Next
    INDEX
    Explanations

    expected behavior or specification

    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
     McA
    -0.09
    ity
    -0.09
    ubi
    -0.08
     Trim
    -0.08
     Nug
    -0.08
    alian
    -0.08
    mland
    -0.08
    (íģ¬ê¸°
    -0.08
     Cunning
    -0.08
    iny
    -0.08
    POSITIVE LOGITS
     will
    0.17
     would
    0.16
     sẽ
    0.14
     бÑĥдеÑĤ
    0.14
    will
    0.12
     sarÃł
    0.12
     akan
    0.12
     бÑĥдÑĥÑĤ
    0.11
     Ø®ÙĪاÙĩد
    0.11
     depends
    0.11
    Activations Density 0.006%

    No Known Activations