Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16420
    Prev
    Next
    INDEX
    Explanations

    discussions about athletic achievements and competitive 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
    ootball
    -0.08
    alytics
    -0.07
    acades
    -0.07
    æĬ¼
    -0.07
    ÑĥÑĩа
    -0.07
    typings
    -0.07
    лини
    -0.07
     Gerr
    -0.07
     Quarterly
    -0.06
    á»įng
    -0.06
    POSITIVE LOGITS
     Olympic
    0.09
     medal
    0.08
     training
    0.08
     representing
    0.08
     Team
    0.07
     performances
    0.07
     World
    0.07
     Training
    0.07
     world
    0.07
     Represent
    0.07
    Activations Density 0.038%

    No Known Activations