© 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. 104034
    Prev
    Next
    INDEX
    Explanations

    numerical data or references to legal cases and regulations

    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
    agua
    -0.07
     latter
    -0.07
    arrera
    -0.07
     reservation
    -0.07
    301
    -0.07
    kova
    -0.07
     Reservation
    -0.06
    lops
    -0.06
    tains
    -0.06
     rezerv
    -0.06
    POSITIVE LOGITS
     Tick
    0.07
    osi
    0.07
    etten
    0.06
    owo
    0.06
     tick
    0.06
     spoken
    0.06
    ioso
    0.06
    isi
    0.06
     Ary
    0.06
    Blue
    0.06
    Activations Density 0.008%

    No Known Activations