© 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. 39973
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rights and recognition in the context of marriage and family

    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
     Tân
    -0.07
    ypress
    -0.06
     ó
    -0.06
    nar
    -0.06
    SV
    -0.06
    istar
    -0.06
     Ñĥгод
    -0.06
    amilies
    -0.06
     nghiá»ĩp
    -0.06
    å¼
    -0.06
    POSITIVE LOGITS
     shares
    0.07
     shared
    0.06
     access
    0.06
     sharing
    0.06
     inherit
    0.06
    shares
    0.06
    otify
    0.06
     co
    0.06
    ãĥ¼ãĥ¬
    0.06
    QUIT
    0.06
    Activations Density 0.010%

    No Known Activations