© 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. 4702
    Prev
    Next
    INDEX
    Explanations

    topics related to sports events and experiences

    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
    ysi
    -0.06
    adows
    -0.06
    ä¼¼
    -0.06
    iry
    -0.06
    ç±
    -0.06
    uli
    -0.06
    essen
    -0.06
    okoj
    -0.06
    rog
    -0.06
    adors
    -0.06
    POSITIVE LOGITS
    _fixture
    0.07
    zig
    0.07
    оÑĢод
    0.07
    ocus
    0.07
     thriller
    0.07
    ixer
    0.07
    /security
    0.06
     funnel
    0.06
    Reserved
    0.06
    .palette
    0.06
    Activations Density 0.044%

    No Known Activations