© 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. 27357
    Prev
    Next
    INDEX
    Explanations

    terms related to trading and gaming outcomes

    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
    ķĮ
    -0.07
    off
    -0.06
     trailing
    -0.06
    wk
    -0.06
     anchors
    -0.06
    pure
    -0.06
    erras
    -0.05
    antz
    -0.05
    zier
    -0.05
    afc
    -0.05
    POSITIVE LOGITS
    ÃĹ</
    0.09
    .raise
    0.07
    ipay
    0.07
    utow
    0.07
    iddi
    0.06
    efon
    0.06
    ritos
    0.06
    ̧
    0.06
     mê
    0.06
    ipse
    0.06
    Activations Density 0.009%

    No Known Activations