© 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. 117360
    Prev
    Next
    INDEX
    Explanations

    programming keywords and functions related to library imports and method definitions

    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
    anzi
    -0.07
    ardu
    -0.07
    usal
    -0.06
    IODevice
    -0.06
    /*------------------------------------------------
    -0.06
    stro
    -0.06
     اÙĦØ£ÙĨ
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    .bundle
    -0.06
    /as
    -0.06
    POSITIVE LOGITS
    opoulos
    0.07
    çļĦæĺ¯
    0.07
    readcr
    0.06
     Vintage
    0.06
    &quot
    0.06
    ignKey
    0.06
    InstanceOf
    0.06
     ÃĤ
    0.06
    ä¸įäºĨ
    0.05
    .asp
    0.05
    Activations Density 0.016%

    No Known Activations