© 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. 16424
    Prev
    Next
    INDEX
    Explanations

    elements related to performance art and improvisation

    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
    ombo
    -0.07
    zim
    -0.07
    _NT
    -0.07
    ManagedObjectContext
    -0.07
    ekil
    -0.07
    rsa
    -0.07
    _TAC
    -0.06
    uitka
    -0.06
    :;"
    -0.06
    egra
    -0.06
    POSITIVE LOGITS
     _
    0.06
    icon
    0.06
    73
    0.06
     unspecified
    0.06
     oneself
    0.06
    óst
    0.06
    ipp
    0.06
    utsch
    0.06
    MT
    0.06
     himself
    0.06
    Activations Density 0.003%

    No Known Activations