© 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. 62489
    Prev
    Next
    INDEX
    Explanations

    references to ancestral or historical connections and the concept of identity

    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
     faire
    -0.07
     Jer
    -0.06
    avax
    -0.06
     adipiscing
    -0.06
    zyst
    -0.06
    PTION
    -0.06
    اجÙĩ
    -0.06
     Fair
    -0.06
    eniz
    -0.06
    oruÄį
    -0.06
    POSITIVE LOGITS
    uish
    0.07
    usz
    0.07
    onymous
    0.06
     Listings
    0.06
    æĢ¥
    0.06
    æľĽ
    0.06
    tim
    0.06
    ãn
    0.06
    adolu
    0.06
     Carnegie
    0.06
    Activations Density 0.037%

    No Known Activations