© 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. 128426
    Prev
    Next
    INDEX
    Explanations

    references to schooling systems and educational methods

    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
    é«ĺæł¡
    -0.07
    ulk
    -0.07
     SETTINGS
    -0.06
     elementary
    -0.06
    839
    -0.06
    amber
    -0.06
    achable
    -0.06
    æľºåħ³
    -0.06
     ç¨
    -0.06
    /XML
    -0.06
    POSITIVE LOGITS
     atmosphere
    0.07
     programs
    0.07
    _CONNECT
    0.06
     staff
    0.06
     arts
    0.06
    letics
    0.06
    sports
    0.06
     uniforms
    0.06
    ardy
    0.06
     Atmos
    0.06
    Activations Density 0.045%

    No Known Activations