© 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. 17617
    Prev
    Next
    INDEX
    Explanations

    person's preference or enjoyment

    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
    æģ¨
    -0.10
     env
    -0.10
     disliked
    -0.10
     dislike
    -0.10
     Kut
    -0.10
     dislikes
    -0.09
     priority
    -0.09
     Bek
    -0.09
    QS
    -0.09
    odie
    -0.09
    POSITIVE LOGITS
     enjoy
    0.21
     enjoys
    0.19
     grav
    0.18
     enjoyed
    0.17
    grav
    0.15
     Enjoy
    0.15
     enjoying
    0.15
    享
    0.15
    åĸľæ¬¢
    0.14
     enjoyment
    0.14
    Activations Density 0.093%

    No Known Activations