© 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. 128922
    Prev
    Next
    INDEX
    Explanations

    references to court districts and federal legal terminology

    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
    jvu
    -0.07
    rer
    -0.07
    /help
    -0.07
    ollen
    -0.07
    GROUND
    -0.06
    ï¼ĪæĺŃåĴĮ
    -0.06
    quette
    -0.06
    .pick
    -0.06
    å®Ļ
    -0.06
    elling
    -0.06
    POSITIVE LOGITS
    s
    0.07
    aus
    0.06
     genu
    0.06
    967
    0.06
    uy
    0.06
    ighb
    0.06
    ODO
    0.06
    ulumi
    0.06
    atcher
    0.06
    OD
    0.06
    Activations Density 0.003%

    No Known Activations