© 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. 125259
    Prev
    Next
    INDEX
    Explanations

    words associated with artistic expression or creativity

    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
    423
    -0.07
    anger
    -0.07
    enden
    -0.07
    ardo
    -0.06
    723
    -0.06
    ULK
    -0.06
     appropriations
    -0.06
    ago
    -0.06
    id
    -0.06
     cosm
    -0.06
    POSITIVE LOGITS
    //{{
    0.10
    Ú¯ÛĮرÛĮ
    0.08
    rve
    0.08
    okable
    0.08
    _CNTL
    0.08
    .AutoComplete
    0.07
    ityEngine
    0.07
    ãĥĩãĤ£ãĥ¼ãĤ¹
    0.07
    -ни
    0.07
    âĦĸ
    0.07
    Activations Density 0.000%

    No Known Activations