© 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. 106256
    Prev
    Next
    INDEX
    Explanations

    specific century-related terms or numerical references that indicate historical time periods

    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
    peria
    -0.08
     ydk
    -0.08
    ÑĢеÑĪ
    -0.08
    emmel
    -0.08
    ãĥªãĥ¼ãĤº
    -0.07
    linkplain
    -0.07
    eced
    -0.07
    ULE
    -0.07
     tavs
    -0.07
    ioned
    -0.07
    POSITIVE LOGITS
    s
    0.09
    th
    0.09
    ï¸ı
    0.08
    ème
    0.06
    į
    0.06
     conv
    0.06
    avel
    0.06
     dispens
    0.06
    st
    0.06
    ÏĤ
    0.06
    Activations Density 0.011%

    No Known Activations