© 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. 15-LLAMASCOPE-RES-131K
    11. 87172
    Prev
    Next
    INDEX
    Explanations

    key events or outcomes in competitive sports

    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
     окÑĢÑĥг
    -0.06
    .loadData
    -0.06
    鬼
    -0.06
    Linear
    -0.06
    getParameter
    -0.06
    Neighbors
    -0.06
     linear
    -0.06
     Linear
    -0.06
     scal
    -0.06
     disorder
    -0.06
    POSITIVE LOGITS
    -final
    0.08
    final
    0.07
     Final
    0.07
    heiro
    0.07
     finals
    0.07
    awe
    0.07
    екÑĤи
    0.07
     final
    0.07
    ensation
    0.06
     rootNode
    0.06
    Activations Density 0.222%

    No Known Activations