© 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. 16455
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and attributes in a software context

    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
    udad
    -0.06
    AdapterManager
    -0.06
    rite
    -0.06
    issan
    -0.06
    reater
    -0.06
    ALLE
    -0.06
     InitializeComponent
    -0.06
    ekil
    -0.06
    ensen
    -0.06
    odyn
    -0.06
    POSITIVE LOGITS
    uger
    0.07
     @{↵
    0.07
    ={"
    0.07
    gh
    0.07
    ":{"
    0.06
    ãĤ¿ãĥ³
    0.06
    ':{'
    0.06
    :↵
    0.06
    ters
    0.06
    ÑĢÑĸд
    0.06
    Activations Density 0.011%

    No Known Activations