© 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. 116534
    Prev
    Next
    INDEX
    Explanations

    geographical references, particularly to African countries, especially Sierra Leone and Liberia

    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
     Indian
    -0.07
     Illinois
    -0.07
    agini
    -0.07
     Halk
    -0.07
    urga
    -0.07
    å½
    -0.06
     Mexico
    -0.06
    .mx
    -0.06
     NAFTA
    -0.06
     Indians
    -0.06
    POSITIVE LOGITS
     Liberia
    0.09
    phia
    0.07
     cocoa
    0.07
     Dias
    0.07
     Ghana
    0.06
    GNU
    0.06
    _tol
    0.06
    ISODE
    0.06
    iture
    0.06
     GPL
    0.06
    Activations Density 0.008%

    No Known Activations