© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    wise / wisdom

    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
    yal
    -0.09
     Weed
    -0.09
     èī¯
    -0.08
     Sellers
    -0.08
    worthy
    -0.08
     Fam
    -0.08
    åħ´
    -0.08
    ework
    -0.08
     indef
    -0.08
     watchdog
    -0.08
    POSITIVE LOGITS
     wisdom
    0.74
     wise
    0.68
     Wisdom
    0.62
     Wise
    0.61
    wise
    0.60
    wis
    0.59
    -wise
    0.57
    Wis
    0.54
     wis
    0.52
    WISE
    0.49
    Activations Density 0.165%

    No Known Activations