© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38861
    Prev
    Next
    INDEX
    Explanations

    beauty and gentle qualities

    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
     swagger
    -0.10
     masculine
    -0.10
     twink
    -0.10
     ëĦ¤ìĿ´íĬ¸
    -0.09
     boy
    -0.09
    luv
    -0.09
    opensource
    -0.09
    yaw
    -0.09
    -boy
    -0.08
    éĽĦ
    -0.08
    POSITIVE LOGITS
     beauty
    0.23
     Beauty
    0.17
    Beauty
    0.16
    ç¾İ
    0.15
     beautiful
    0.15
     herself
    0.15
     beaut
    0.14
     eth
    0.14
     fragile
    0.14
     purity
    0.14
    Activations Density 0.164%

    No Known Activations