© 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. 94552
    Prev
    Next
    INDEX
    Explanations

    elements related to events, gatherings, and live broadcasts

    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
     Workshop
    -0.06
     Spam
    -0.06
    VERTEX
    -0.06
     вÑģп
    -0.06
    -spinner
    -0.06
     workshops
    -0.06
     Dennis
    -0.06
    eland
    -0.05
    æµ®
    -0.05
    ilet
    -0.05
    POSITIVE LOGITS
     live
    0.14
     Live
    0.13
     livest
    0.13
    live
    0.12
    -live
    0.12
     video
    0.12
    缴æĴŃ
    0.12
    Live
    0.11
     LIVE
    0.11
    _live
    0.11
    Activations Density 0.150%

    No Known Activations