© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one" and its variations, reflecting emphasis on singular entities

    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
     various
    -0.08
     Various
    -0.07
    ses
    -0.07
     themselves
    -0.07
    ias
    -0.07
    331
    -0.06
    ÑĢо
    -0.06
    pas
    -0.06
    ãģ¹ãģį
    -0.06
    atic
    -0.06
    POSITIVE LOGITS
     instance
    0.09
    instance
    0.08
    ê
    0.08
     INSTANCE
    0.07
    /Dk
    0.07
    akedirs
    0.07
    readcr
    0.07
    ÙĮ
    0.07
    -half
    0.07
    ennie
    0.07
    Activations Density 0.028%

    No Known Activations