© 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. 50166
    Prev
    Next
    INDEX
    Explanations

    maximum health or hit points

    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
    ç
    -0.10
     mole
    -0.09
    egend
    -0.09
    :.:
    -0.09
    esson
    -0.09
    haar
    -0.09
     çap
    -0.09
     Hou
    -0.09
    rella
    -0.09
    mue
    -0.08
    POSITIVE LOGITS
     health
    0.33
     HP
    0.30
     Health
    0.27
    HP
    0.25
     hp
    0.24
    health
    0.24
    hp
    0.23
    Health
    0.23
    -health
    0.19
     здоÑĢов
    0.18
    Activations Density 0.059%

    No Known Activations