© 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. 1300
    Prev
    Next
    INDEX
    Explanations

    references to companies and their activities in the business context

    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
    ackson
    -0.07
     Krish
    -0.06
    erves
    -0.06
    unken
    -0.06
     surrogate
    -0.06
    emies
    -0.06
    رات
    -0.06
    ujet
    -0.06
    lsa
    -0.06
    arra
    -0.06
    POSITIVE LOGITS
    utor
    0.07
     vi
    0.07
    uard
    0.07
    _mD
    0.07
    assin
    0.07
    596
    0.06
    HashCode
    0.06
    KER
    0.06
    .createClass
    0.06
    âu
    0.06
    Activations Density 0.100%

    No Known Activations