© 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. 79632
    Prev
    Next
    INDEX
    Explanations

    references to "hoops" and related words, indicating an interest in activities or events surrounding hoops, such as performances or competitions

    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
    isas
    -0.08
    ulers
    -0.07
    омÑĸ
    -0.07
    inceton
    -0.07
    uggy
    -0.07
    literal
    -0.07
    tle
    -0.07
    cams
    -0.07
    ìļ±
    -0.07
     pri
    -0.06
    POSITIVE LOGITS
    fer
    0.08
    -shaped
    0.07
    ress
    0.07
    lessly
    0.07
    stress
    0.07
    ote
    0.07
    sted
    0.06
    iston
    0.06
    foot
    0.06
    adoop
    0.06
    Activations Density 0.003%

    No Known Activations