© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89862
    Prev
    Next
    INDEX
    Explanations

    references to the character Antigone and themes related to her story in Greek tragedies

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    sworth
    -0.09
    ckt
    -0.08
    æŀľ
    -0.08
    esi
    -0.08
    RICS
    -0.07
    rik
    -0.07
    orman
    -0.07
    enheim
    -0.07
    ä»»
    -0.07
    ewood
    -0.07
    POSITIVE LOGITS
    enna
    0.08
    icrobial
    0.07
    eced
    0.07
    elope
    0.07
    iet
    0.07
     Ant
    0.07
    uitive
    0.07
    Ú©Ùĩ
    0.06
     McCart
    0.06
    ony
    0.06
    Activations Density 0.038%

    No Known Activations