© 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. 78763
    Prev
    Next
    INDEX
    Explanations

    action and performance-related phrases 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
    jin
    -0.07
     handle
    -0.06
    orna
    -0.06
    bro
    -0.06
    siz
    -0.06
    up
    -0.05
     Barr
    -0.05
    l
    -0.05
    utch
    -0.05
     up
    -0.05
    POSITIVE LOGITS
    adden
    0.07
    orgia
    0.07
    amus
    0.07
    ãĤ¤ãĥī
    0.07
    bero
    0.07
     passe
    0.07
    .Marshal
    0.07
    ryo
    0.07
    uyo
    0.07
    Ļ¨
    0.07
    Activations Density 0.028%

    No Known Activations