© 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 EvalsExportsAPI 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. 125665
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries and frameworks

    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
    andy
    -0.06
    /configuration
    -0.06
     =
    -0.06
     Yates
    -0.05
    otto
    -0.05
     strict
    -0.05
    odo
    -0.05
     auditor
    -0.05
     absol
    -0.05
    etro
    -0.05
    POSITIVE LOGITS
    imd
    0.07
    .TXT
    0.07
    /../
    0.07
     ÑĤой
    0.07
    ../
    0.07
    ä¿Ĭ
    0.07
    .sap
    0.07
    emain
    0.07
    -utils
    0.07
    ops
    0.07
    Activations Density 0.008%

    No Known Activations