© 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. 17-LLAMASCOPE-RES-131K
    11. 74968
    Prev
    Next
    INDEX
    Explanations

    references to former athletes and their professional backgrounds

    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
    lei
    -0.07
    ÑĪÑĮ
    -0.06
    ẫ
    -0.06
     oku
    -0.06
    anmar
    -0.06
    poÄį
    -0.06
    olin
    -0.06
     sole
    -0.06
     än
    -0.06
    -ÑĤо
    -0.06
    POSITIVE LOGITS
    urt
    0.07
    arget
    0.06
    inct
    0.06
    zap
    0.06
    ÅĤug
    0.06
     Sentry
    0.06
     cellspacing
    0.06
    rief
    0.06
    rine
    0.06
    cest
    0.06
    Activations Density 0.002%

    No Known Activations