© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 95928
    Prev
    Next
    INDEX
    Explanations

    headings and summary statements in the text

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

    Section headings or introductory phrases (especially "Introduction") that precede and organize the main content of a document.

    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
    ëįĶ
    -0.07
    åĩºãģĹ
    -0.07
    iev
    -0.07
    rought
    -0.07
    волÑı
    -0.07
    longleftrightarrow
    -0.07
    actionDate
    -0.07
    надлеж
    -0.07
    inki
    -0.07
    ););↵
    -0.07
    POSITIVE LOGITS
     This
    0.07
    aire
    0.06
    This
    0.06
    -this
    0.06
     Lorem
    0.06
     purpose
    0.06
     Dixon
    0.06
    lund
    0.06
    atos
    0.06
    etto
    0.06
    Activations Density 0.019%

    No Known Activations