© 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. 105889
    Prev
    Next
    INDEX
    Explanations

    references to specific plants and their health benefits

    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
    ework
    -0.06
    Ñĥков
    -0.06
     ********************************************************************************
    -0.06
    ëŀij
    -0.06
    Ñĭл
    -0.06
     seç
    -0.06
     oby
    -0.06
     Classics
    -0.06
     guild
    -0.06
    Lights
    -0.06
    POSITIVE LOGITS
     health
    0.08
     benefits
    0.08
    health
    0.08
     properties
    0.08
    properties
    0.07
    Properties
    0.07
     medicine
    0.07
    kenin
    0.07
     Benefits
    0.07
    enef
    0.07
    Activations Density 0.026%

    No Known Activations