© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38267
    Prev
    Next
    INDEX
    Explanations

    quirky descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    quirky, absurd, or whimsical descriptions and actions.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @yooniel31
    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
    Negative Logits
     Dia
    -0.09
    ảnh
    -0.09
    .scalablytyped
    -0.09
    nock
    -0.09
     whit
    -0.09
    ULE
    -0.08
    eci
    -0.08
    igroup
    -0.08
     humanoid
    -0.08
    ;
    -0.08
    POSITIVE LOGITS
     instead
    0.10
    ieber
    0.09
    rne
    0.09
     edition
    0.09
     Genius
    0.09
     enc
    0.09
    ogo
    0.09
     вмеÑģÑĤ
    0.08
    instead
    0.08
    åİ»äºĨ
    0.08
    Activations Density 0.176%

    No Known Activations