© 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. 39472
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the," particularly in contexts involving measurements or evaluations of behavior

    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
     оÑĩеÑĢедÑĮ
    -0.07
    ocard
    -0.06
    yard
    -0.06
    .Solid
    -0.06
    ictor
    -0.06
    ixture
    -0.06
    cene
    -0.06
    оÑĢон
    -0.06
    rating
    -0.06
    _submenu
    -0.06
    POSITIVE LOGITS
     seus
    0.10
     his
    0.10
     seu
    0.09
     suo
    0.09
     your
    0.08
     suas
    0.08
    ä»ĸçļĦ
    0.08
     suoi
    0.07
     sua
    0.07
     его
    0.07
    Activations Density 0.195%

    No Known Activations