© 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. 86685
    Prev
    Next
    INDEX
    Explanations

    references to legal assistance and support

    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
    )prepare
    -0.06
    Jamie
    -0.06
    ailable
    -0.06
    uais
    -0.06
     Jamie
    -0.06
    LEAN
    -0.06
    uro
    -0.06
    UMP
    -0.06
    gne
    -0.06
    OSC
    -0.06
    POSITIVE LOGITS
    icum
    0.07
     moden
    0.06
    onical
    0.06
    eÅŁ
    0.06
    utas
    0.06
    usercontent
    0.06
    icates
    0.06
    orest
    0.06
    .onView
    0.06
    оÑĢдин
    0.06
    Activations Density 0.003%

    No Known Activations