© 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. 28023
    Prev
    Next
    INDEX
    Explanations

    references to government entities, particularly federal institutions

    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
    ela
    -0.09
    ETIME
    -0.07
    ematic
    -0.07
    мов
    -0.07
    lah
    -0.07
    _CSR
    -0.07
    ELS
    -0.07
    athing
    -0.06
    ioc
    -0.06
    eting
    -0.06
    POSITIVE LOGITS
    ized
    0.13
    ization
    0.11
    izes
    0.11
    izing
    0.10
    ised
    0.10
    ize
    0.10
    mente
    0.09
    isation
    0.08
    izers
    0.08
    ogy
    0.08
    Activations Density 0.006%

    No Known Activations