© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107046
    Prev
    Next
    INDEX
    Explanations

    words related to cultural and historical themes

    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
    activex
    -0.07
    DataContract
    -0.06
     such
    -0.06
    ÑijÑĢ
    -0.06
    zhou
    -0.06
    apan
    -0.06
    .cd
    -0.06
    ând
    -0.06
    Č↵
    -0.06
    -0.06
    POSITIVE LOGITS
    olated
    0.07
    imbus
    0.07
    /auto
    0.06
    ustum
    0.06
    phan
    0.06
    �t
    0.06
    &t
    0.06
     career
    0.06
    coes
    0.06
    ÑĨÑĸйно
    0.06
    Activations Density 0.031%

    No Known Activations