© 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. 116361
    Prev
    Next
    INDEX
    Explanations

    names of people and their roles in the production of films

    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
    arella
    -0.07
    ubl
    -0.07
    arend
    -0.06
    vfs
    -0.06
    Bond
    -0.06
    ifest
    -0.06
    missions
    -0.06
     اÙĦØ°
    -0.06
     Hispan
    -0.06
    istar
    -0.06
    POSITIVE LOGITS
    essler
    0.07
     additional
    0.07
    erre
    0.07
    enson
    0.07
     Additional
    0.06
    eria
    0.06
     recurs
    0.06
     Ni
    0.06
    Ä±ÅŁma
    0.06
     Mine
    0.06
    Activations Density 0.003%

    No Known Activations