© 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. 91573
    Prev
    Next
    INDEX
    Explanations

    terms related to passengers and passenger capacity

    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
    ÑģÑĮ
    -0.07
    ãģ£ãģ±
    -0.07
    enty
    -0.07
    avor
    -0.07
    UserDefaults
    -0.07
    puts
    -0.07
    anche
    -0.06
    ippi
    -0.06
    anic
    -0.06
    gies
    -0.06
    POSITIVE LOGITS
    hip
    0.09
    hood
    0.09
    /client
    0.08
    /student
    0.08
    geber
    0.07
    hips
    0.07
     who
    0.07
     ³³ ³³
    0.07
    -only
    0.07
     whom
    0.06
    Activations Density 0.004%

    No Known Activations