© 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. 129834
    Prev
    Next
    INDEX
    Explanations

    references to achievements and statistics 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
    ä¸įåı¯
    -0.07
    λικ
    -0.07
    ìħ
    -0.06
    Unified
    -0.06
    hammad
    -0.06
    747
    -0.06
    obody
    -0.06
    unkt
    -0.06
    ê¹Į
    -0.06
    оÑĤов
    -0.06
    POSITIVE LOGITS
     twice
    0.09
    ector
    0.07
     Peel
    0.07
    retty
    0.07
     runner
    0.07
     numerous
    0.06
     rec
    0.06
    kov
    0.06
     Bronze
    0.06
     runners
    0.06
    Activations Density 0.016%

    No Known Activations