© 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. 75919
    Prev
    Next
    INDEX
    Explanations

    elements related to scoring and gameplay in sports

    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
    alles
    -0.08
     completo
    -0.07
    allee
    -0.07
    ivec
    -0.07
    ocos
    -0.07
     Bilim
    -0.07
    ÑĪин
    -0.07
    zeÅĦ
    -0.07
    SceneManager
    -0.07
     DevComponents
    -0.07
    POSITIVE LOGITS
     early
    0.12
     late
    0.11
    early
    0.10
    late
    0.09
     Early
    0.09
    Early
    0.08
     Late
    0.08
     earlier
    0.07
     during
    0.07
    Late
    0.07
    Activations Density 0.017%

    No Known Activations