© 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. 89129
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft PowerPoint and related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The word "PowerPoint" (or "PPT" as an abbreviation) referring to Microsoft's presentation software, appearing in contexts related to professional skills listings, training materials, presentations, or educational resources.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    thouse
    -0.06
    oya
    -0.06
    SCP
    -0.06
     laps
    -0.06
    ampp
    -0.06
    ged
    -0.06
    زد
    -0.06
    .Highlight
    -0.06
    خاÙĨÙĩ
    -0.06
    /providers
    -0.05
    POSITIVE LOGITS
     presentations
    0.08
     presentation
    0.07
     Pow
    0.07
     Presentation
    0.07
     PowerPoint
    0.07
    ente
    0.07
    βολ
    0.07
    imson
    0.07
    presentation
    0.07
    aux
    0.07
    Activations Density 0.012%

    No Known Activations