© 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. 34340
    Prev
    Next
    INDEX
    Explanations

    healthy and youthful

    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
    OfSize
    -0.11
     flourishing
    -0.10
    FromClass
    -0.10
    SimpleName
    -0.09
     åĸ
    -0.09
     ëĦ¤ìĿ´íĬ¸
    -0.09
    EMPLARY
    -0.09
    affer
    -0.09
    574
    -0.09
     egregious
    -0.09
    POSITIVE LOGITS
     healthy
    0.26
     happy
    0.19
    healthy
    0.18
     Healthy
    0.18
    åģ¥åº·
    0.17
     alert
    0.15
    happy
    0.15
     content
    0.15
     well
    0.15
     HEALTH
    0.15
    Activations Density 0.109%

    No Known Activations