© 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. 74053
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to ancient empires, particularly the Byzantine Empire

    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
    utenberg
    -0.09
    190
    -0.08
    phinx
    -0.08
    icerca
    -0.08
    rypton
    -0.08
    166
    -0.08
     Laden
    -0.07
    phins
    -0.07
    lesc
    -0.07
     fkk
    -0.07
    POSITIVE LOGITS
     AD
    0.08
     Byz
    0.08
    AD
    0.08
     Justin
    0.07
     Vand
    0.07
     Romance
    0.07
    Justin
    0.07
     Winchester
    0.06
     Garland
    0.06
     Roger
    0.06
    Activations Density 0.058%

    No Known Activations