© 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. 38369
    Prev
    Next
    INDEX
    Explanations

    du experiencing illness

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of illness or physical symptoms (e.g., infections, swelling) in health-related contexts, including in non-English text.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
     bladder
    -0.10
     болезни
    -0.10
    çĻ
    -0.09
     bowel
    -0.09
     ÑĤва
    -0.09
     oscill
    -0.09
     Erd
    -0.09
     впол
    -0.09
     afflict
    -0.09
     famine
    -0.09
    POSITIVE LOGITS
     feel
    0.14
    sym
    0.14
     feels
    0.13
     pain
    0.13
    çĹĽ
    0.13
     felt
    0.13
    felt
    0.12
     pains
    0.12
     dolor
    0.12
     Ow
    0.12
    Activations Density 0.290%

    No Known Activations