© 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. 28812
    Prev
    Next
    INDEX
    Explanations

    detailed statistical data and information about trade and production across various countries

    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
    ùng
    -0.07
    uyến
    -0.07
    оÑĢаз
    -0.07
    пÑĢимеÑĢ
    -0.07
     gratuits
    -0.07
     hete
    -0.07
     æĵ
    -0.07
    Äħż
    -0.07
    éļª
    -0.07
    .TXT
    -0.06
    POSITIVE LOGITS
     trend
    0.07
     Din
    0.07
     report
    0.07
     data
    0.07
     sector
    0.06
    emain
    0.06
     trends
    0.06
     tables
    0.06
    ienes
    0.06
    baseline
    0.06
    Activations Density 0.012%

    No Known Activations