© 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. 27034
    Prev
    Next
    INDEX
    Explanations

    references to international relations between countries

    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
    owell
    -0.08
    ãĤ¹ãĤ¿ãĥ¼
    -0.07
    leans
    -0.07
    ocha
    -0.07
    ÑĪе
    -0.07
    ÙĨسÙĬØ©
    -0.07
    idelberg
    -0.07
    tie
    -0.07
    OwnProperty
    -0.07
    FRING
    -0.07
    POSITIVE LOGITS
     others
    0.07
     partners
    0.06
    enerator
    0.06
     industry
    0.06
    ahl
    0.06
     Others
    0.06
    auth
    0.06
     authorities
    0.06
     allies
    0.06
     Swe
    0.06
    Activations Density 0.025%

    No Known Activations