© 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. 54288
    Prev
    Next
    INDEX
    Explanations

    feelings of emotions/states

    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
    ä¸Ģç§į
    -0.21
    ä¸ĢäºĽ
    -0.18
    ä¸ĢåĢĭ
    -0.15
    ä¸ĢåĪĩ
    -0.13
     sense
    -0.12
    ä¸Ģ
    -0.12
    ä¸ĢçĤ¹
    -0.12
    à¸Ħà¸ĵะ
    -0.11
     Sense
    -0.11
    à¸ľ
    -0.10
    POSITIVE LOGITS
     sorts
    0.13
     utmost
    0.12
     utter
    0.12
     being
    0.11
     extreme
    0.11
    /from
    0.11
     alarm
    0.10
    monds
    0.10
    ellig
    0.10
     absolute
    0.10
    Activations Density 0.071%

    No Known Activations