© 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. 85996
    Prev
    Next
    INDEX
    Explanations

    directional wind conditions and meteorological terms

    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
    icer
    -0.09
    criptor
    -0.08
    ære
    -0.07
    iaux
    -0.07
    umbledore
    -0.07
    ourg
    -0.07
    -Level
    -0.07
     numberWith
    -0.07
    ieme
    -0.07
    ailand
    -0.07
    POSITIVE LOGITS
    /left
    0.07
    ward
    0.06
    /N
    0.06
    ides
    0.06
    ses
    0.06
    rible
    0.06
    CI
    0.06
    wards
    0.06
     accent
    0.06
    Direction
    0.06
    Activations Density 0.002%

    No Known Activations