© 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. 82284
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the busyness and complexity of situations

    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
    orda
    -0.07
    elon
    -0.07
    ilden
    -0.06
    ónica
    -0.06
     Solo
    -0.06
    Solo
    -0.06
    ë¯
    -0.06
    elves
    -0.06
    §è¡Į
    -0.06
    oze
    -0.06
    POSITIVE LOGITS
     ones
    0.39
     Ones
    0.24
    ones
    0.22
     one
    0.20
    ãĤĤãģ®
    0.16
    .ones
    0.14
    ONES
    0.13
     others
    0.13
     uno
    0.10
     ours
    0.10
    Activations Density 0.111%

    No Known Activations