© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 104781
    Prev
    Next
    INDEX
    Explanations

    specific cultural or traditional practices related to dance

    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
    cta
    -0.06
    eman
    -0.06
    zsche
    -0.06
    ÙĬتÙĬ
    -0.06
     Mage
    -0.06
    orsch
    -0.06
    hausen
    -0.06
    .ribbon
    -0.06
    Cls
    -0.06
    #=
    -0.06
    POSITIVE LOGITS
     performed
    0.07
     practiced
    0.07
    STALL
    0.07
    ucht
    0.06
     evolved
    0.06
     horizontal
    0.06
    ybrid
    0.06
    abd
    0.06
     ve
    0.06
     cond
    0.06
    Activations Density 0.018%

    No Known Activations