© 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. 108574
    Prev
    Next
    INDEX
    Explanations

    links and references to online resources or services

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

    Website listing elements including timestamps, URLs, service categories, and HTML structural components often appearing in directory-style content.

    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
     ,.
    -0.07
     :.
    -0.07
    Ãłng
    -0.07
     ue
    -0.07
    claimer
    -0.06
    :.
    -0.06
    .ToolTip
    -0.06
    .InnerException
    -0.06
    atsby
    -0.06
    á»ĵi
    -0.06
    POSITIVE LOGITS
    uitka
    0.07
    ÄĽle
    0.07
    :UITableView
    0.07
    actionDate
    0.07
    using
    0.07
    _customize
    0.06
    ÄĽn
    0.06
    iyel
    0.06
    âĢ¬
    0.06
    $MESS
    0.06
    Activations Density 0.293%

    No Known Activations