© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 47301
    Prev
    Next
    INDEX
    Explanations

    critics accusing, would argue, believed

    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
    Negative Logits
     accord
    -0.10
     lip
    -0.09
    otron
    -0.09
    lixir
    -0.09
    abwe
    -0.09
    aar
    -0.09
    716
    -0.09
     ãĤĿ
    -0.08
     discussed
    -0.08
     dissent
    -0.08
    POSITIVE LOGITS
     argument
    0.28
     argue
    0.26
     argued
    0.24
     arguing
    0.23
    arg
    0.22
     arg
    0.22
     Argument
    0.22
    argument
    0.21
     argues
    0.21
     arguments
    0.21
    Activations Density 0.063%

    No Known Activations