© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    feeling pleased or excited

    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
    487
    -0.10
     sounding
    -0.09
     MainMenu
    -0.08
    åĬŀ
    -0.08
    aking
    -0.08
    å¸
    -0.08
     nond
    -0.08
    uffy
    -0.08
     Sass
    -0.08
    eru
    -0.08
    POSITIVE LOGITS
    çľĭåĪ°
    0.11
     seeing
    0.10
    bserv
    0.10
     hearing
    0.10
     tiener
    0.10
    äºİ
    0.09
    ÄĽn
    0.09
    inka
    0.09
    oso
    0.09
     vì
    0.09
    Activations Density 0.077%

    No Known Activations