© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 125623
    Prev
    Next
    INDEX
    Explanations

    words related to decorative elements and aesthetics

    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
    uyla
    -0.08
    EDIUM
    -0.07
    ı
    -0.07
    βολ
    -0.07
    สาย
    -0.07
    CreateInfo
    -0.07
    ARGIN
    -0.07
     electrónico
    -0.07
    ÅĽmy
    -0.07
    ÃŃ
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.12
    ing
    0.12
    dür
    0.08
    ï¸
    0.08
    amp
    0.08
    erif
    0.08
    ev
    0.07
    âĨĴâĨĴ
    0.07
    ONS
    0.06
    elsius
    0.06
    Activations Density 0.389%

    No Known Activations