© 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. 121630
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and procedures regarding content ownership and copyright

    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
    atos
    -0.07
    inki
    -0.07
    igest
    -0.06
    473
    -0.06
    /people
    -0.06
     verk
    -0.06
    öt
    -0.06
    erken
    -0.06
    arge
    -0.06
    adu
    -0.06
    POSITIVE LOGITS
     below
    0.07
     reverse
    0.06
     section
    0.06
    .dd
    0.06
    Reverse
    0.06
     Wenger
    0.06
    pNet
    0.06
    боÑĤ
    0.06
    _literals
    0.06
    elper
    0.06
    Activations Density 0.003%

    No Known Activations