© 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 EvalsExportsAPI 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. 29370
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotations in narrative

    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
    embed
    -0.07
    ãģ¥
    -0.06
    lamaz
    -0.06
    âĢĮ
    -0.06
    figcaption
    -0.06
     cvs
    -0.06
    agini
    -0.06
    елÑĸ
    -0.06
     suprem
    -0.06
    oso
    -0.06
    POSITIVE LOGITS
    ysi
    0.07
     Nationwide
    0.07
     tek
    0.07
    orst
    0.06
     blo
    0.06
     aba
    0.06
    mine
    0.06
     cos
    0.06
    kip
    0.06
    449
    0.06
    Activations Density 0.400%

    No Known Activations