© 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. 58740
    Prev
    Next
    INDEX
    Explanations

    references to professional wrestling events, specifically WrestleMania

    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
    elon
    -0.07
     gest
    -0.06
     dialogs
    -0.06
    ureau
    -0.06
    HWND
    -0.06
    eled
    -0.06
    agus
    -0.06
     germ
    -0.06
     SaÄŁ
    -0.06
    財
    -0.06
    POSITIVE LOGITS
     event
    0.07
    ushima
    0.07
     Event
    0.07
    Event
    0.07
    Live
    0.07
    EventArgs
    0.07
     Annual
    0.07
     Live
    0.07
     annual
    0.07
    event
    0.07
    Activations Density 0.006%

    No Known Activations