© 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. 92594
    Prev
    Next
    INDEX
    Explanations

    key terms related to analysis and classification across various contexts

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

    Section headers, navigation elements, or content titles that appear at content boundaries or page transitions.

    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
     знов
    -0.08
    iele
    -0.08
    acy
    -0.08
     suy
    -0.08
     vá»įng
    -0.07
     ì¦
    -0.07
     Ãĸzel
    -0.07
     UITableViewController
    -0.07
    ots
    -0.07
     Чи
    -0.07
    POSITIVE LOGITS
     bacheca
    0.07
     manufacture
    0.06
    ..↵
    0.06
    0.06
    liers
    0.06
    isté
    0.06
     ..↵
    0.06
     !↵
    0.05
    tabpanel
    0.05
    uddy
    0.05
    Activations Density 0.197%

    No Known Activations