© 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. 17-LLAMASCOPE-RES-131K
    11. 88272
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and actions

    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
    azen
    -0.07
    iali
    -0.07
    -based
    -0.07
    stown
    -0.06
    rze
    -0.06
     Pret
    -0.06
    ikal
    -0.06
    æĸ¹éĿ¢
    -0.06
    è¡
    -0.06
    -Based
    -0.06
    POSITIVE LOGITS
     Alla
    0.07
    trag
    0.07
     Latter
    0.07
     phẩm
    0.06
     edilen
    0.06
    ToUpper
    0.06
    rieved
    0.06
    ÑĢиг
    0.06
    ä¹Ļ
    0.06
    /reference
    0.06
    Activations Density 0.046%

    No Known Activations