© 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. 130936
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to district attorneys

    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
    ÃŁe
    -0.07
    åľ°ä¸ĭ
    -0.07
     imageSize
    -0.07
    ritch
    -0.07
     Legisl
    -0.06
     vess
    -0.06
    prene
    -0.06
    Å¡ti
    -0.06
    deen
    -0.06
     scouting
    -0.06
    POSITIVE LOGITS
     charging
    0.07
     cases
    0.07
    /ion
    0.07
     Bureau
    0.07
    674
    0.07
    리ìĸ´
    0.07
    xdb
    0.07
     AG
    0.07
    _ATTACH
    0.06
    _jet
    0.06
    Activations Density 0.084%

    No Known Activations