© 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. 91510
    Prev
    Next
    INDEX
    Explanations

    statistics or data-related content

    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
     localVar
    -0.07
    ystore
    -0.06
    ترÛĮ
    -0.06
    obia
    -0.06
    ells
    -0.06
    .LayoutStyle
    -0.06
    oxel
    -0.06
     fisse
    -0.06
     PTR
    -0.06
     vents
    -0.06
    POSITIVE LOGITS
     pair
    0.07
    _pair
    0.07
     PROCUREMENT
    0.07
     votes
    0.07
     poll
    0.07
    æķĹ
    0.06
    our
    0.06
     elimination
    0.06
     Dispatch
    0.06
    Pair
    0.06
    Activations Density 0.004%

    No Known Activations