© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88206
    Prev
    Next
    INDEX
    Explanations

    references to horse racing events and terminology

    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
    ÐIJÑĢÑħÑĸв
    -0.08
    ADOR
    -0.08
    asket
    -0.08
    ectl
    -0.08
    иденÑĤ
    -0.07
     Goat
    -0.07
    Ø¡
    -0.07
    swick
    -0.07
    ÑĨик
    -0.07
    acula
    -0.07
    POSITIVE LOGITS
     discount
    0.07
     should
    0.06
     pot
    0.06
     this
    0.06
     trying
    0.06
     mo
    0.06
     has
    0.05
     discounts
    0.05
    ervations
    0.05
     is
    0.05
    Activations Density 0.013%

    No Known Activations