© 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. 77314
    Prev
    Next
    INDEX
    Explanations

    references to computational processes and conditions in programming contexts

    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
    omed
    -0.08
    sted
    -0.07
    GINE
    -0.07
     kê
    -0.07
     civilization
    -0.07
    ALLE
    -0.07
    quil
    -0.07
    idine
    -0.07
     brave
    -0.06
    oms
    -0.06
    POSITIVE LOGITS
    ç¯
    0.07
    rift
    0.06
    .setLocation
    0.06
    .jsoup
    0.06
    >Returns
    0.06
    оÑı
    0.06
    еÑĢÑĤв
    0.06
    åģ
    0.05
    cks
    0.05
    νηÏĤ
    0.05
    Activations Density 0.222%

    No Known Activations