© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    creative acts and originality

    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
    å¼ĭ
    -0.09
    .setViewport
    -0.09
     destabil
    -0.08
    tin
    -0.08
     Arn
    -0.08
    yor
    -0.08
    幸
    -0.08
    ãĢĥ
    -0.08
     Flo
    -0.08
    ths
    -0.08
    POSITIVE LOGITS
     creativity
    0.49
     creative
    0.44
     Creat
    0.39
    Creat
    0.38
    creative
    0.36
     creat
    0.35
     ÑĤвоÑĢ
    0.34
     Creative
    0.33
    Creative
    0.32
     imagination
    0.31
    Activations Density 0.167%

    No Known Activations