© 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. 77777
    Prev
    Next
    INDEX
    Explanations

    names of countries and geographic locations

    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
    aban
    -0.09
    tam
    -0.07
     tam
    -0.07
    trand
    -0.07
     Presence
    -0.07
     Pap
    -0.07
    allet
    -0.07
    åħ°
    -0.06
     Lange
    -0.06
     Rand
    -0.06
    POSITIVE LOGITS
    rices
    0.08
     Baz
    0.08
     Gaz
    0.07
    avez
    0.07
     maz
    0.07
    Incre
    0.07
    laz
    0.07
    ález
    0.07
    pegawai
    0.07
    yaw
    0.07
    Activations Density 0.023%

    No Known Activations