© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89485
    Prev
    Next
    INDEX
    Explanations

    terms related to transactions and documentation

    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
    artner
    -0.06
    MouseButton
    -0.06
     letter
    -0.05
    ToFront
    -0.05
    :type
    -0.05
    ØŃÙħ
    -0.05
    kea
    -0.05
    mada
    -0.05
    reator
    -0.05
     lets
    -0.05
    POSITIVE LOGITS
    udo
    0.08
    Wiki
    0.07
    wik
    0.07
    oda
    0.07
    acula
    0.07
    lush
    0.07
    adr
    0.07
    pcf
    0.07
    _revision
    0.07
    BOT
    0.06
    Activations Density 0.001%

    No Known Activations