© 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. 62506
    Prev
    Next
    INDEX
    Explanations

    the presence of statistics and numerical data in a context related to games or 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
    olo
    -0.06
    adel
    -0.06
     ëĵ¤
    -0.06
    ỹ
    -0.06
    ubb
    -0.06
    uve
    -0.06
    adol
    -0.06
    oli
    -0.06
     mari
    -0.06
    यन
    -0.06
    POSITIVE LOGITS
    æł
    0.06
    eid
    0.06
     sole
    0.06
    bine
    0.06
    ledi
    0.06
    euillez
    0.06
    kes
    0.06
    eza
    0.06
    ÑĦа
    0.06
    irable
    0.06
    Activations Density 0.001%

    No Known Activations