© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of vehicles or machinery

    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
    iyat
    -0.06
    #
    -0.06
    -append
    -0.06
    antz
    -0.06
    obot
    -0.06
    linger
    -0.06
     publicly
    -0.06
     пÑĢоиз
    -0.05
    using
    -0.05
     наз
    -0.05
    POSITIVE LOGITS
    vat
    0.08
    éĽĨä¸Ń
    0.07
    regon
    0.07
     ked
    0.07
    Integral
    0.07
    idar
    0.07
    .weixin
    0.07
    ÅĻ
    0.07
    ÃŃme
    0.07
    .factory
    0.07
    Activations Density 0.000%

    No Known Activations