© 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. 87879
    Prev
    Next
    INDEX
    Explanations

    themes related to the concept of America as a diverse and complex nation

    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
    lice
    -0.06
     ep
    -0.06
    avin
    -0.06
     fier
    -0.06
    ier
    -0.06
    ilm
    -0.06
     Victorian
    -0.06
    uf
    -0.06
    icense
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
     American
    0.12
     America
    0.11
    American
    0.11
     Americans
    0.10
    America
    0.10
     Mỹ
    0.10
    american
    0.10
    merican
    0.10
    ãĤ¢ãĥ¡ãĥªãĤ«
    0.09
    -Americ
    0.09
    Activations Density 0.040%

    No Known Activations