© 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. 19502
    Prev
    Next
    INDEX
    Explanations

    health and wellness impact

    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
     Psychiatry
    -0.12
     Psychiat
    -0.12
     psychiat
    -0.10
    istrovstvÃŃ
    -0.10
     antidepress
    -0.10
     меÑĤалли
    -0.09
     Toxic
    -0.09
     extr
    -0.09
     Meadow
    -0.08
     tarif
    -0.08
    POSITIVE LOGITS
     health
    0.43
     medical
    0.40
     healthcare
    0.37
     Health
    0.33
    health
    0.32
    medical
    0.30
    -health
    0.29
     Medical
    0.29
    Health
    0.29
    åĮ»çĸĹ
    0.28
    Activations Density 0.229%

    No Known Activations