© 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. 124189
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures, particularly related to Armenian history

    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
     Indones
    -0.08
     Jacksonville
    -0.08
     Niger
    -0.07
     Nigeria
    -0.07
    leep
    -0.06
    .dtd
    -0.06
     Indonesian
    -0.06
     Nigerian
    -0.06
    íĥķ
    -0.06
     Pie
    -0.06
    POSITIVE LOGITS
     Armenian
    0.15
     Armenia
    0.15
     Armen
    0.12
    Õ
    0.09
     Beirut
    0.08
     вÑĸÑĢ
    0.08
     Lebanon
    0.07
     Geg
    0.07
    yan
    0.07
    nicos
    0.07
    Activations Density 0.017%

    No Known Activations