© 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. 108947
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation and automated vehicle interactions

    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
    uels
    -0.08
    mue
    -0.08
    vu
    -0.07
    еÑĢÑĤи
    -0.07
    iverz
    -0.07
    loating
    -0.07
    вÑĥ
    -0.07
    ä¸Ī
    -0.07
    amp
    -0.07
    lder
    -0.07
    POSITIVE LOGITS
     Manual
    0.07
     manual
    0.07
     override
    0.07
     overrides
    0.07
    GridColumn
    0.06
    Manual
    0.06
     hands
    0.06
    /manual
    0.06
    jar
    0.06
    adb
    0.06
    Activations Density 0.002%

    No Known Activations