© 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. 4535
    Prev
    Next
    INDEX
    Explanations

    themes related to educational institutions and services

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

    Short promotional taglines or mission statements that appear between a website's header/title and main content, serving as concise brand positioning statements.

    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
    ochen
    -0.07
    ptrdiff
    -0.06
    ersen
    -0.06
    recio
    -0.06
    ̧
    -0.06
    floor
    -0.06
    otta
    -0.06
    erap
    -0.06
    WARDED
    -0.06
    rint
    -0.06
    POSITIVE LOGITS
     Welcome
    0.13
     welcome
    0.13
    Welcome
    0.13
    welcome
    0.09
    elcome
    0.09
    ELCOME
    0.08
    >Welcome
    0.07
     welcomed
    0.07
     welcomes
    0.07
    欢
    0.07
    Activations Density 0.121%

    No Known Activations