© 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. 15-LLAMASCOPE-RES-131K
    11. 89800
    Prev
    Next
    INDEX
    Explanations

    terms related to authority and power dynamics within a fictional or political context

    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
    ardon
    -0.09
    dete
    -0.08
    retim
    -0.07
    grese
    -0.07
    tera
    -0.07
    sumer
    -0.07
    taj
    -0.07
    atte
    -0.07
     ConfigurationManager
    -0.07
    ÑĦеÑĢ
    -0.07
    POSITIVE LOGITS
     Quarter
    0.06
     Geoffrey
    0.06
     Consortium
    0.06
     unstable
    0.06
     slow
    0.05
     quarter
    0.05
    _compile
    0.05
    è©ķ
    0.05
     ex
    0.05
     hors
    0.05
    Activations Density 0.002%

    No Known Activations