© 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. 60076
    Prev
    Next
    INDEX
    Explanations

    references to time periods or durations

    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
    ene
    -0.06
    lass
    -0.06
    ène
    -0.06
    essler
    -0.06
     bore
    -0.06
    affle
    -0.06
    rait
    -0.06
    _Local
    -0.06
    ENE
    -0.05
    ounce
    -0.05
    POSITIVE LOGITS
    ìŀĦ
    0.08
    zew
    0.07
    Ù¾ÛĮ
    0.07
     since
    0.07
    ince
    0.07
    etimes
    0.07
    êm
    0.07
    zell
    0.07
    itech
    0.07
    ago
    0.07
    Activations Density 0.013%

    No Known Activations