© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    references to significant film franchises and their legacy

    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
    enza
    -0.07
    鬼
    -0.06
    ç±
    -0.06
     Raq
    -0.06
    oes
    -0.06
     Sakura
    -0.06
    /Edit
    -0.06
     Mister
    -0.06
     floor
    -0.06
     gem
    -0.06
    POSITIVE LOGITS
     franchise
    0.07
    ãĥ¼ãĥ«ãĥī
    0.07
     VÅ¡ech
    0.07
    Wars
    0.06
    iosper
    0.06
     Sho
    0.06
    athed
    0.06
    appid
    0.06
    ottage
    0.06
     franch
    0.06
    Activations Density 0.013%

    No Known Activations