© 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. 81549
    Prev
    Next
    INDEX
    Explanations

    references to agreements, grants, and funding-related terms in educational and governmental 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
     backed
    -0.07
    SDL
    -0.06
     Arbit
    -0.06
    IFS
    -0.05
     ey
    -0.05
    osoph
    -0.05
    ami
    -0.05
     obsolete
    -0.05
     ev
    -0.05
     Avg
    -0.05
    POSITIVE LOGITS
    asiswa
    0.08
     bÃło
    0.08
    Sci
    0.07
    egrity
    0.07
     nghiá»ĩm
    0.07
     èij
    0.07
    inness
    0.07
    program
    0.07
    eltas
    0.07
     chặt
    0.07
    Activations Density 0.002%

    No Known Activations