© 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 EvalsExportsAPI 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. 88316
    Prev
    Next
    INDEX
    Explanations

    instances of celebration or scoring in sports contexts

    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
     обоÑĢ
    -0.08
    _feed
    -0.07
    emploi
    -0.07
    кол
    -0.07
    .extensions
    -0.07
    гл
    -0.07
    afort
    -0.06
    tl
    -0.06
    feeding
    -0.06
     pů
    -0.06
    POSITIVE LOGITS
    anja
    0.07
     declar
    0.07
    ü
    0.06
    addtogroup
    0.06
    leton
    0.06
    aspect
    0.06
    Aspect
    0.06
    Äĩe
    0.06
     Pole
    0.06
     Aspect
    0.06
    Activations Density 0.003%

    No Known Activations