© 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. 73183
    Prev
    Next
    INDEX
    Explanations

    closing braces and preprocessor directives in code

    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
    anda
    -0.07
    лем
    -0.07
    ActionResult
    -0.06
    EMA
    -0.06
    oa
    -0.06
     éħ
    -0.06
     putas
    -0.06
    eras
    -0.06
    ema
    -0.06
     semiclass
    -0.06
    POSITIVE LOGITS
     (
    0.07
     (`
    0.06
    ilde
    0.06
    äºľ
    0.06
    ÙĪاج
    0.06
    asmine
    0.06
    ä¿Ĭ
    0.06
    izar
    0.06
    oples
    0.06
    warts
    0.06
    Activations Density 0.022%

    No Known Activations