© 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. 126649
    Prev
    Next
    INDEX
    Explanations

    references to educational levels, curricula, and academic objectives

    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
    Å¡k
    -0.07
    afka
    -0.06
    /sys
    -0.06
    ochen
    -0.06
    awai
    -0.06
     Libraries
    -0.06
    InBackground
    -0.05
    âĢ¦↵
    -0.05
    ata
    -0.05
     programmes
    -0.05
    POSITIVE LOGITS
    'gc
    0.09
    LIK
    0.08
     promin
    0.07
     entreprene
    0.07
    ÐŁÐļ
    0.07
    ingham
    0.07
    AndHashCode
    0.07
     åĨĨ
    0.07
    ceb
    0.07
     bis
    0.07
    Activations Density 0.003%

    No Known Activations