© 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. 107112
    Prev
    Next
    INDEX
    Explanations

    key events and actions in a racing context

    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
    ë¡ľëĤĺ
    -0.07
    ä¹Ĺ
    -0.07
    redo
    -0.07
    RELEASE
    -0.07
    à¹Ĥ
    -0.06
    >manual
    -0.06
    istrovstvÃŃ
    -0.06
    phem
    -0.06
    ÑĢоиз
    -0.06
     Rai
    -0.06
    POSITIVE LOGITS
     lap
    0.07
    Leader
    0.06
    dar
    0.06
     Leader
    0.06
    aby
    0.06
     obed
    0.06
    obia
    0.06
    lap
    0.06
    leader
    0.06
    efe
    0.06
    Activations Density 0.020%

    No Known Activations