© 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. 84281
    Prev
    Next
    INDEX
    Explanations

    references to medical terms and studies

    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
    otts
    -0.08
    utschen
    -0.07
    IMIT
    -0.07
    aguay
    -0.07
    plist
    -0.07
    celik
    -0.07
    houette
    -0.07
    ystick
    -0.07
    \Migration
    -0.07
    lescope
    -0.06
    POSITIVE LOGITS
     fundamentals
    0.08
     Essentials
    0.08
     Fund
    0.08
     essentials
    0.07
     basics
    0.07
     course
    0.07
    course
    0.07
     Principles
    0.07
    Ñıж
    0.07
     principles
    0.06
    Activations Density 0.041%

    No Known Activations