© 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. 126626
    Prev
    Next
    INDEX
    Explanations

    military and service-related terminology

    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
    \<^
    -0.06
    /as
    -0.06
    imos
    -0.05
    747
    -0.05
    AW
    -0.05
     spoken
    -0.05
    ighbors
    -0.05
     Eig
    -0.05
    ÑĮ
    -0.05
    iew
    -0.05
    POSITIVE LOGITS
    activex
    0.07
    annel
    0.06
    otts
    0.06
    elm
    0.06
    rolls
    0.06
    жа
    0.06
    :convert
    0.06
    argon
    0.06
     mơ
    0.06
     Creature
    0.06
    Activations Density 0.001%

    No Known Activations