© 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. 9-LLAMASCOPE-RES-131K
    11. 94124
    Prev
    Next
    INDEX
    Explanations

    references to school transportation, specifically school buses

    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
    usize
    -0.07
     nature
    -0.06
    nature
    -0.06
    avia
    -0.06
    ears
    -0.06
    æ¡IJ
    -0.06
    abor
    -0.06
    rike
    -0.06
     ActionTypes
    -0.06
     lean
    -0.06
    POSITIVE LOGITS
    .codec
    0.07
    Safety
    0.07
     Safety
    0.06
    .ERR
    0.06
    jen
    0.06
    Ñģли
    0.06
     safety
    0.06
    .signals
    0.06
    ersed
    0.06
    -thumbnails
    0.06
    Activations Density 0.003%

    No Known Activations