© 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 EvalsExportsAPI 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. 58977
    Prev
    Next
    INDEX
    Explanations

    references to the "Star Wars" franchise

    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
    erson
    -0.07
    ersion
    -0.07
    ymous
    -0.06
    esters
    -0.06
    etics
    -0.06
    YZ
    -0.06
    erv
    -0.06
    ors
    -0.06
    chaft
    -0.06
    egers
    -0.06
    POSITIVE LOGITS
    bucks
    0.10
    vation
    0.10
     Wars
    0.09
    kest
    0.09
    utory
    0.09
     Trek
    0.08
    zman
    0.08
    burst
    0.08
     ç¨
    0.07
     wars
    0.07
    Activations Density 0.013%

    No Known Activations