© 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. 129712
    Prev
    Next
    INDEX
    Explanations

    references to property-related procedures and regulations

    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
    جا
    -0.08
    ÛĮرÙĩ
    -0.07
    ÑĸдÑĥ
    -0.07
    ä¹ĺ
    -0.07
    (=)
    -0.07
    ugar
    -0.07
    eton
    -0.07
    target
    -0.07
    unate
    -0.07
    ZeroWidthSpace
    -0.07
    POSITIVE LOGITS
     boundary
    0.08
     Boundary
    0.07
     mov
    0.07
     property
    0.06
    achi
    0.06
    boundary
    0.06
    Boundary
    0.06
     beyond
    0.06
     legally
    0.06
     Border
    0.06
    Activations Density 0.001%

    No Known Activations