© 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. 129603
    Prev
    Next
    INDEX
    Explanations

    references to student involvement and activities in educational contexts

    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
    ctp
    -0.07
    ignant
    -0.07
    åįĴ
    -0.07
    arta
    -0.06
    iversit
    -0.06
    aptive
    -0.06
    [block
    -0.06
    OFF
    -0.06
    igua
    -0.06
     Grad
    -0.06
    POSITIVE LOGITS
     Science
    0.07
     Advisor
    0.07
    reek
    0.07
     science
    0.06
     teens
    0.06
    Arduino
    0.06
    è¿IJ
    0.06
     Teens
    0.06
    åĬ±
    0.06
     Display
    0.06
    Activations Density 0.003%

    No Known Activations