© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80067
    Prev
    Next
    INDEX
    Explanations

    aspects of theatrical production design, particularly focusing on elaborate sets and costumes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     kontakte
    -0.07
    Invoker
    -0.06
     Backpack
    -0.06
    ï¼ļ"
    -0.06
    /docs
    -0.06
    ofilm
    -0.06
     seins
    -0.06
    659
    -0.06
     Dra
    -0.06
    chants
    -0.06
    POSITIVE LOGITS
     stage
    0.10
     Stage
    0.09
     scenery
    0.08
    stage
    0.08
    (stage
    0.07
    Stage
    0.07
     staging
    0.07
     stages
    0.07
     scen
    0.07
    ública
    0.07
    Activations Density 0.018%

    No Known Activations