© 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. 27628
    Prev
    Next
    INDEX
    Explanations

    research findings

    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
     aud
    -0.10
     Difference
    -0.09
     hum
    -0.09
     Elevated
    -0.08
    oton
    -0.08
    715
    -0.08
     celular
    -0.08
    685
    -0.08
    _TB
    -0.08
    ẩn
    -0.08
    POSITIVE LOGITS
     studies
    0.20
     research
    0.17
     Studies
    0.14
    çłĶ究
    0.13
    research
    0.13
     knock
    0.13
    Studies
    0.12
     Research
    0.12
    Research
    0.12
    udies
    0.12
    Activations Density 0.094%

    No Known Activations