© 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. 72399
    Prev
    Next
    INDEX
    Explanations

    references to the movie "La La Land."

    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
    çĢ
    -0.06
    eren
    -0.06
    assis
    -0.06
    鬼
    -0.06
     sag
    -0.06
    __,__
    -0.06
    ltk
    -0.06
    .gateway
    -0.06
     Melania
    -0.06
    eca
    -0.06
    POSITIVE LOGITS
     Heavenly
    0.07
    -vertical
    0.06
    LOS
    0.06
     Los
    0.06
     Academy
    0.06
     LA
    0.06
    ikal
    0.06
    .mapbox
    0.06
     Dream
    0.06
     Metro
    0.06
    Activations Density 0.002%

    No Known Activations