© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    references to creative roles and experiences within the advertising or design industry

    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
    .annot
    -0.07
    ogene
    -0.06
    avic
    -0.06
    .mit
    -0.06
    amat
    -0.06
    tÃŃ
    -0.06
    uml
    -0.06
    ifu
    -0.06
    arya
    -0.06
    serialized
    -0.06
    POSITIVE LOGITS
     agency
    0.15
    Agency
    0.13
     agencies
    0.13
    agency
    0.13
     Agency
    0.12
     Agencies
    0.11
     PR
    0.10
     campaigns
    0.10
     Brand
    0.09
     Campaign
    0.09
    Activations Density 0.185%

    No Known Activations