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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76670
    Prev
    Next
    INDEX
    Explanations

    references to athletes and their roles or contributions in various 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
    peration
    -0.07
    edis
    -0.07
    gorm
    -0.07
     voks
    -0.07
    agle
    -0.07
    ILES
    -0.07
    Verts
    -0.07
     trp
    -0.07
    _PTR
    -0.07
    loat
    -0.07
    POSITIVE LOGITS
     athlete
    0.09
     Ath
    0.07
     athletes
    0.07
    360
    0.06
    getPlayer
    0.06
     IMG
    0.06
     player
    0.06
     Marketable
    0.06
     micro
    0.06
     Auth
    0.06
    Activations Density 0.002%

    No Known Activations