© 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. 63061
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization and tailored design in complex systems

    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
    enco
    -0.06
    ifer
    -0.06
    oldem
    -0.06
    imet
    -0.06
    /Foundation
    -0.06
    own
    -0.06
    eday
    -0.06
    ttl
    -0.06
    esen
    -0.06
    lot
    -0.06
    POSITIVE LOGITS
     CONTRIBUTORS
    0.08
    ÑĢом
    0.07
    mani
    0.07
     Cousins
    0.07
     vendor
    0.07
     Vendor
    0.07
     DCHECK
    0.07
     PROCUREMENT
    0.07
    setter
    0.07
    ysa
    0.07
    Activations Density 0.000%

    No Known Activations