© 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. 108800
    Prev
    Next
    INDEX
    Explanations

    titles related to managerial or directorial positions

    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
    alama
    -0.08
    ALCHEMY
    -0.07
    лаж
    -0.07
     mó
    -0.07
    anka
    -0.07
    祥
    -0.07
    åĪĹ
    -0.07
    ermen
    -0.07
    ANJI
    -0.06
    ÙĨج
    -0.06
    POSITIVE LOGITS
     of
    0.08
    åħ¼
    0.07
    urator
    0.07
    entifier
    0.07
    serter
    0.07
    ủa
    0.06
    /Dk
    0.06
     \/
    0.06
     của
    0.06
     Bail
    0.06
    Activations Density 0.014%

    No Known Activations