© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103404
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person's debut or introduction in a specific context or role

    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
    åªĴ
    -0.07
     Gül
    -0.07
    ISCO
    -0.07
    à¸Ńà¸ĩ
    -0.07
    нож
    -0.07
    MESS
    -0.07
    ãĥ¬ãĤ¹
    -0.07
    /Dk
    -0.07
    emmel
    -0.07
    alles
    -0.07
    POSITIVE LOGITS
     whopping
    0.06
    cko
    0.05
     hostile
    0.05
    _authenticated
    0.05
    urger
    0.05
     sal
    0.05
     Cald
    0.05
     Twin
    0.05
    aps
    0.05
     lên
    0.05
    Activations Density 0.001%

    No Known Activations