© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 87937
    Prev
    Next
    INDEX
    Explanations

    references to actors and actresses in film and theater contexts

    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
    memberof
    -0.07
    unct
    -0.07
    erior
    -0.07
     McCabe
    -0.07
    venture
    -0.06
    ters
    -0.06
    andering
    -0.06
    alm
    -0.06
    antt
    -0.06
    OLEAN
    -0.06
    POSITIVE LOGITS
     BaseController
    0.08
     blitz
    0.07
    âĺĨ
    0.07
    .Designer
    0.07
    hung
    0.06
    izu
    0.06
    /react
    0.06
     Fist
    0.06
    ê
    0.06
    еÑĢжав
    0.06
    Activations Density 0.001%

    No Known Activations