© 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. 17-LLAMASCOPE-RES-131K
    6. 29831
    Prev
    Next
    INDEX
    Explanations

    references to traditional Korean foods and drinks

    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
    bild
    -0.06
    urious
    -0.06
     кÑĥ
    -0.06
    irts
    -0.06
    oda
    -0.06
    -bars
    -0.06
    465
    -0.05
    agnar
    -0.05
    cie
    -0.05
    vault
    -0.05
    POSITIVE LOGITS
    ä¸Ģç§į
    0.10
    utor
    0.08
    akin
    0.07
    ickness
    0.07
    utors
    0.06
     सद
    0.06
     аналог
    0.06
    ÑĥÑĩа
    0.06
    ,__
    0.06
    anel
    0.06
    Activations Density 0.030%

    No Known Activations