© 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. 53755
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to scientific and engineering fields

    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
     weather
    -0.07
    enant
    -0.07
    weather
    -0.07
    627
    -0.06
     Weather
    -0.06
    ungan
    -0.06
     ump
    -0.06
     ngu
    -0.06
    optera
    -0.06
     mud
    -0.06
    POSITIVE LOGITS
     blood
    0.09
     medical
    0.09
     Blood
    0.08
     Medical
    0.08
    medical
    0.08
     biomedical
    0.08
    LOOD
    0.07
     tissue
    0.07
     Depth
    0.07
    ç´į
    0.07
    Activations Density 0.002%

    No Known Activations