© 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. 15-LLAMASCOPE-RES-131K
    11. 90785
    Prev
    Next
    INDEX
    Explanations

    elements related to gaming mechanics and player interactions

    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
    inka
    -0.07
    alez
    -0.06
    ndef
    -0.06
    nees
    -0.06
    endra
    -0.06
    uš
    -0.06
    erce
    -0.06
    aims
    -0.06
    ılı
    -0.06
    etest
    -0.06
    POSITIVE LOGITS
    afen
    0.06
    wr
    0.06
     crunch
    0.06
    Ļ¨
    0.06
    iani
    0.06
    loquent
    0.06
     tort
    0.06
    bsolute
    0.06
     Hun
    0.06
    Courtesy
    0.06
    Activations Density 0.004%

    No Known Activations