© 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. 9-LLAMASCOPE-RES-131K
    11. 95835
    Prev
    Next
    INDEX
    Explanations

    terms related to gaming mechanics and elements

    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
     close
    -0.06
     sem
    -0.06
     pur
    -0.06
     fortified
    -0.06
    el
    -0.06
    a
    -0.06
     weather
    -0.06
    s
    -0.05
    es
    -0.05
    elson
    -0.05
    POSITIVE LOGITS
    ounge
    0.08
    /Instruction
    0.08
    Stamped
    0.07
    .ali
    0.07
    BindingUtil
    0.07
    .XtraPrinting
    0.07
    NetMessage
    0.07
    átis
    0.07
    _Lean
    0.07
    edom
    0.07
    Activations Density 0.000%

    No Known Activations