© 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. 3641
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal services and law practices

    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
    oss
    -0.07
     geom
    -0.07
    ruk
    -0.06
    оÑıн
    -0.06
    ä»®
    -0.06
    eti
    -0.06
    TOOLS
    -0.06
    лаж
    -0.06
    rg
    -0.06
    æĦ
    -0.06
    POSITIVE LOGITS
    utherford
    0.06
    aq
    0.06
    _MAGIC
    0.06
    acre
    0.06
    697
    0.06
     SetLastError
    0.06
    \Client
    0.06
    Å¡em
    0.06
    /Area
    0.06
    inka
    0.06
    Activations Density 0.014%

    No Known Activations