© 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. 103944
    Prev
    Next
    INDEX
    Explanations

    terms associated with socio-economic and cultural impacts in West Africa

    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
     bev
    -0.07
    .Designer
    -0.07
    ivant
    -0.06
    wand
    -0.06
    abbr
    -0.06
     cavern
    -0.06
    ekli
    -0.06
    erer
    -0.06
     treff
    -0.06
    rar
    -0.06
    POSITIVE LOGITS
    odes
    0.07
    ÏĦο
    0.07
     Census
    0.06
    arkin
    0.06
    Tube
    0.06
     ном
    0.06
    çĶº
    0.06
     spatial
    0.06
    changer
    0.06
     dise
    0.06
    Activations Density 0.001%

    No Known Activations