© 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. 70532
    Prev
    Next
    INDEX
    Explanations

    symbols, legal terms, and directives related to software licensing and permissions

    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
     nackte
    -0.08
    alore
    -0.07
    antu
    -0.07
    ι
    -0.07
    isko
    -0.07
    ingleton
    -0.07
    ayed
    -0.07
     ÑĨÑĸй
    -0.07
     mysl
    -0.07
    ryo
    -0.07
    POSITIVE LOGITS
    nbsp
    0.07
     Henrik
    0.06
    Wire
    0.06
     how
    0.06
    /or
    0.06
     Wort
    0.05
    _wire
    0.05
     Trial
    0.05
    Bounding
    0.05
    uran
    0.05
    Activations Density 0.001%

    No Known Activations