© 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. 15-LLAMASCOPE-RES-131K
    11. 87557
    Prev
    Next
    INDEX
    Explanations

    references to sections and introductions in documents

    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
    ynos
    -0.09
    nemonic
    -0.07
    dej
    -0.07
    -Israel
    -0.07
    usercontent
    -0.07
    itable
    -0.07
    ducible
    -0.07
    curity
    -0.07
    enan
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
    AYER
    0.08
    ayer
    0.08
     Luxury
    0.06
     incididunt
    0.06
    Wie
    0.06
    pb
    0.06
    Nib
    0.06
     ÑģоÑĩ
    0.06
    ickets
    0.06
     Schul
    0.06
    Activations Density 0.003%

    No Known Activations