© 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. 30468
    Prev
    Next
    INDEX
    Explanations

    snippets of code or technical language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    hee
    -0.07
    ̣
    -0.06
    568
    -0.06
    ä½Ļ
    -0.06
    cke
    -0.06
    539
    -0.06
    steen
    -0.06
    ÑĢÑĥг
    -0.06
    quette
    -0.06
     zoekt
    -0.06
    POSITIVE LOGITS
     setTitle
    0.08
    TITLE
    0.08
    .setTitle
    0.07
    ufen
    0.07
    :title
    0.07
    (title
    0.07
    =title
    0.07
    abras
    0.07
     title
    0.07
    /title
    0.06
    Activations Density 0.000%

    No Known Activations