© 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 EvalsExportsinterp-engineNEWAPI 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. 89349
    Prev
    Next
    INDEX
    Explanations

    instances of high activation related to promotional content or calls to action

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

    Formatting markers that indicate section or content boundaries in documents, often appearing at transition points between different text blocks or at the beginning/end of content sections.

    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
    ercul
    -0.06
    ects
    -0.05
    yah
    -0.05
     Humb
    -0.05
    tero
    -0.05
    imbus
    -0.05
     Dys
    -0.05
    ÎIJ
    -0.05
    Truthy
    -0.05
     coinc
    -0.05
    POSITIVE LOGITS
    kul
    0.08
    .undefined
    0.08
    iaux
    0.07
    ÙİÙĪ
    0.07
    æĢĴ
    0.07
    리그
    0.07
    formace
    0.07
    pez
    0.07
    grese
    0.06
    ÑĨÑĸ
    0.06
    Activations Density 0.042%

    No Known Activations