© 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. 63268
    Prev
    Next
    INDEX
    Explanations

    specific roles or identities tied to geographical or social affiliations

    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
    enda
    -0.07
    iska
    -0.07
    urge
    -0.07
    lug
    -0.07
    bern
    -0.06
    gratis
    -0.06
    hl
    -0.06
    aeda
    -0.06
    amus
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    )((((
    0.06
    .VideoCapture
    0.06
     thang
    0.06
    udu
    0.06
    ìĤ¬ìĿ´
    0.06
    rots
    0.06
     courtesy
    0.06
     transplant
    0.06
     Jack
    0.06
    otel
    0.05
    Activations Density 0.021%

    No Known Activations