© 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. 89727
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or place names

    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
    óst
    -0.08
    iyon
    -0.08
    ijd
    -0.08
    amedi
    -0.08
    orce
    -0.08
    asje
    -0.07
    urrets
    -0.07
    tems
    -0.07
    äs
    -0.07
    amment
    -0.07
    POSITIVE LOGITS
    es
    0.07
    ere
    0.07
     Crab
    0.07
     Cove
    0.06
     Sokol
    0.06
     goog
    0.06
    ive
    0.06
     protective
    0.06
    .binding
    0.06
     impl
    0.06
    Activations Density 0.013%

    No Known Activations