© 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. 86605
    Prev
    Next
    INDEX
    Explanations

    references to creativity and creative endeavors

    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
    nie
    -0.07
    umu
    -0.07
    Sdk
    -0.07
    ono
    -0.07
    slaught
    -0.07
    é³´
    -0.07
     sm
    -0.06
    IFICATION
    -0.06
    lington
    -0.06
    sm
    -0.06
    POSITIVE LOGITS
    orks
    0.06
    aris
    0.06
    Ž
    0.06
     commons
    0.06
     getUserId
    0.06
    ../../../
    0.06
    /Open
    0.06
    fore
    0.06
     Bec
    0.06
    ¯
    0.06
    Activations Density 0.009%

    No Known Activations