© 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. 9-LLAMASCOPE-RES-131K
    11. 94038
    Prev
    Next
    INDEX
    Explanations

    references to cultural heritage and identity

    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
    quez
    -0.08
    reek
    -0.08
    azÄĥ
    -0.07
    uze
    -0.07
    ằng
    -0.07
    luet
    -0.07
    FINITE
    -0.07
    umed
    -0.07
    mojom
    -0.07
     voks
    -0.07
    POSITIVE LOGITS
     traditional
    0.06
    iden
    0.06
     Ged
    0.06
     Hull
    0.06
     Tar
    0.05
     Dublin
    0.05
     Intr
    0.05
     Ireland
    0.05
     Springer
    0.05
     bo
    0.05
    Activations Density 0.003%

    No Known Activations