© 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. 33096
    Prev
    Next
    INDEX
    Explanations

    overall health and well-being

    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
    ä¹Ī
    -0.09
    brains
    -0.09
     mercy
    -0.09
    ___\n\n
    -0.08
     Morm
    -0.08
    idot
    -0.08
     ï¼İ
    -0.08
    566
    -0.08
    à¥įतन
    -0.08
     minds
    -0.08
    POSITIVE LOGITS
     health
    0.17
    health
    0.13
     well
    0.12
     wellbeing
    0.12
    ç´ł
    0.11
     welfare
    0.11
    -being
    0.11
    /general
    0.10
    ìłģìĿ¸
    0.10
     quality
    0.10
    Activations Density 0.009%

    No Known Activations