© 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. 57425
    Prev
    Next
    INDEX
    Explanations

    occurrences of student engagement and participation in learning activities

    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
    -0.08
    .scalablytyped
    -0.07
    clc
    -0.07
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.07
    _compiler
    -0.07
    amient
    -0.07
    AccessException
    -0.07
    irut
    -0.07
    aki
    -0.07
     YÃĸ
    -0.07
    POSITIVE LOGITS
     understand
    0.07
     themselves
    0.07
     remix
    0.06
    dea
    0.06
    713
    0.06
    ants
    0.06
    ets
    0.06
     invent
    0.06
     Ambient
    0.06
    811
    0.06
    Activations Density 0.026%

    No Known Activations