© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 543
    Prev
    Next
    INDEX
    Explanations

    people-pleasing, fulfilling needs

    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
     fulfilled
    -0.10
     relieved
    -0.10
    mie
    -0.10
    pers
    -0.09
     bothered
    -0.09
    éĤª
    -0.09
    902
    -0.09
    ario
    -0.09
     welcoming
    -0.09
     fulfillment
    -0.09
    POSITIVE LOGITS
     pleasing
    0.39
     appe
    0.38
     plac
    0.37
     please
    0.36
     ple
    0.34
     Ñĥгод
    0.32
     Ple
    0.30
     pleased
    0.30
     impress
    0.30
    please
    0.29
    Activations Density 0.126%

    No Known Activations