© 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. 29229
    Prev
    Next
    INDEX
    Explanations

    actions related to collaboration and engagement 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
    .scalablytyped
    -0.09
    illard
    -0.07
    IDO
    -0.07
    icas
    -0.07
    èŃ
    -0.07
     Williamson
    -0.06
    ido
    -0.06
    _dispatch
    -0.06
    lightbox
    -0.06
    antino
    -0.06
    POSITIVE LOGITS
    regor
    0.07
    egt
    0.07
     aft
    0.07
    -Origin
    0.06
     ha
    0.06
     rub
    0.06
     completed
    0.06
     appropriation
    0.06
     final
    0.06
    juan
    0.06
    Activations Density 0.003%

    No Known Activations