© 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. 80617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ranking or comparison

    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
    ients
    -0.07
    nez
    -0.07
    nt
    -0.06
    |array
    -0.06
    ž
    -0.06
    زا
    -0.06
    uated
    -0.06
    ми
    -0.06
     indeed
    -0.06
    ant
    -0.06
    POSITIVE LOGITS
     everything
    0.09
     already
    0.08
    inton
    0.08
     being
    0.08
    fdc
    0.07
    olley
    0.07
    -bottom
    0.07
    ạn
    0.07
     toho
    0.07
    rawer
    0.07
    Activations Density 0.003%

    No Known Activations