© 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. 15-LLAMASCOPE-RES-131K
    11. 86215
    Prev
    Next
    INDEX
    Explanations

    concepts related to exploration and advancements in space travel

    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
    thane
    -0.07
     snap
    -0.07
    orge
    -0.07
     Freak
    -0.07
    ection
    -0.07
    fas
    -0.07
    oleon
    -0.07
    trak
    -0.06
     Gentle
    -0.06
    munition
    -0.06
    POSITIVE LOGITS
     habit
    0.07
    Gatt
    0.07
     Twig
    0.07
     beyond
    0.07
     Nimbus
    0.06
     Teddy
    0.06
    üçük
    0.06
     Beyond
    0.06
    ü
    0.06
    eniz
    0.06
    Activations Density 0.008%

    No Known Activations