© 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. 31507
    Prev
    Next
    INDEX
    Explanations

    questions related to Greek drama and its characteristics

    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
    ey
    -0.07
    ne
    -0.07
    g
    -0.06
    idis
    -0.06
    otte
    -0.06
    ingt
    -0.06
    ech
    -0.06
    JA
    -0.06
    amine
    -0.06
    gun
    -0.06
    POSITIVE LOGITS
     Does
    0.11
    .Does
    0.09
     Чи
    0.09
     does
    0.09
     How
    0.08
    -how
    0.08
    ãģ©
    0.08
     how
    0.07
    Does
    0.07
     Is
    0.07
    Activations Density 0.003%

    No Known Activations