© 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. 108751
    Prev
    Next
    INDEX
    Explanations

    terms related to film production and screenwriting

    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
    iae
    -0.07
     Albums
    -0.06
     appearances
    -0.06
    stanov
    -0.06
    lá
    -0.06
    igh
    -0.06
     appearance
    -0.06
    outh
    -0.06
    fore
    -0.06
    aga
    -0.06
    POSITIVE LOGITS
     screenplay
    0.09
     pitch
    0.09
     Pitch
    0.08
    Pitch
    0.08
     pitching
    0.08
     Screen
    0.08
    Screen
    0.07
    .pitch
    0.07
     script
    0.07
    pitch
    0.07
    Activations Density 0.002%

    No Known Activations