© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 121347
    Prev
    Next
    INDEX
    Explanations

    humorous interactions and performances in a comedic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zion
    -0.07
    byn
    -0.07
    ofilm
    -0.07
    ometown
    -0.06
    aptive
    -0.06
    [_
    -0.06
    rocess
    -0.06
    jem
    -0.06
    arkin
    -0.06
    .pan
    -0.06
    POSITIVE LOGITS
     imitation
    0.08
     simulate
    0.07
     imperson
    0.07
    imiter
    0.07
     mim
    0.07
     mimic
    0.07
    Unnamed
    0.07
    STALL
    0.06
    simulate
    0.06
    ì§ĵ
    0.06
    Activations Density 0.038%

    No Known Activations