© 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. 61461
    Prev
    Next
    INDEX
    Explanations

    comedian's routines and audience interaction

    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
    æĪı
    -0.10
     humorous
    -0.09
     humour
    -0.09
    835
    -0.09
    ods
    -0.09
    lish
    -0.09
     scoff
    -0.09
    atron
    -0.09
     mockery
    -0.08
    Composer
    -0.08
    POSITIVE LOGITS
     stand
    0.30
     routines
    0.22
     Stand
    0.21
    stand
    0.19
    Stand
    0.18
     SN
    0.18
     routine
    0.16
     observational
    0.16
     sketch
    0.16
    Com
    0.15
    Activations Density 0.087%

    No Known Activations