© 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. 41808
    Prev
    Next
    INDEX
    Explanations

    references to information and its availability across different 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
    OR
    -0.07
    urance
    -0.07
    aldo
    -0.07
    hiba
    -0.06
    olie
    -0.06
    lee
    -0.06
    .getElements
    -0.06
    oris
    -0.06
     Oliv
    -0.06
    ariat
    -0.06
    POSITIVE LOGITS
     about
    0.11
    about
    0.09
     tentang
    0.07
     vá»ģ
    0.07
    egl
    0.07
     such
    0.06
    !=(
    0.06
     ways
    0.06
    paque
    0.06
    ardy
    0.06
    Activations Density 0.013%

    No Known Activations