© 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 EvalsExportsinterp-engineNEWAPI 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. 70369
    Prev
    Next
    INDEX
    Explanations

    instances of participation and engagement in social or communal events

    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
    ObjectContext
    -0.07
    pedia
    -0.07
    rack
    -0.06
    .Butter
    -0.06
    ILLE
    -0.06
    readcr
    -0.06
    _usec
    -0.06
     заÑĢаз
    -0.06
    ivor
    -0.06
    orda
    -0.06
    POSITIVE LOGITS
     new
    0.22
    new
    0.18
     novel
    0.18
    -new
    0.17
     unfamiliar
    0.17
     newly
    0.16
     debut
    0.16
    à¹ĥหม
    0.15
     mỼi
    0.15
    (new
    0.15
    Activations Density 0.245%

    No Known Activations