© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78566
    Prev
    Next
    INDEX
    Explanations

    names of political figures and leaders

    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
    :UITableView
    -0.08
    ÃľM
    -0.08
    mî
    -0.07
     queryInterface
    -0.06
    มà¸Ń
    -0.06
    огÑĢаÑĦ
    -0.06
    uby
    -0.06
    ursal
    -0.06
    rek
    -0.06
    attached
    -0.06
    POSITIVE LOGITS
    -President
    0.07
    -president
    0.07
     aut
    0.07
     President
    0.07
    æ²¢
    0.06
    é¢Ĩ导
    0.06
     president
    0.06
    chg
    0.06
    lant
    0.06
     PM
    0.06
    Activations Density 0.061%

    No Known Activations