© 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. 38435
    Prev
    Next
    INDEX
    Explanations

    references to countries and regions, particularly the UK and the US

    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
    gili
    -0.07
     kå
    -0.07
    afort
    -0.07
     Yön
    -0.07
     Pru
    -0.07
    象
    -0.07
    á»Ĩ
    -0.07
    .Generation
    -0.06
    ective
    -0.06
    thern
    -0.06
    POSITIVE LOGITS
     resident
    0.08
    ç±į
    0.08
    ward
    0.07
     residents
    0.06
     emb
    0.06
    -based
    0.06
    -only
    0.06
     residence
    0.06
    -wide
    0.06
    lish
    0.06
    Activations Density 0.020%

    No Known Activations