© 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. 75607
    Prev
    Next
    INDEX
    Explanations

    terms related to military history and organizations

    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
    igli
    -0.06
    Calendar
    -0.06
    ków
    -0.06
    lessly
    -0.05
    keletal
    -0.05
    ki
    -0.05
    letal
    -0.05
    iyas
    -0.05
    orem
    -0.05
    ów
    -0.05
    POSITIVE LOGITS
    ogui
    0.08
    .setViewport
    0.07
    _Valid
    0.07
    #aa
    0.07
    blr
    0.07
    ायर
    0.07
    ëŀĢ
    0.07
    анÑĤаж
    0.07
    .getElements
    0.07
    ãĥ
    0.07
    Activations Density 0.042%

    No Known Activations