© 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. 128418
    Prev
    Next
    INDEX
    Explanations

    terms related to military and defense topics

    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
    окÑĢем
    -0.07
    едак
    -0.06
     Moines
    -0.06
    Mapped
    -0.06
    eling
    -0.06
    ̣
    -0.06
    icket
    -0.06
     Guys
    -0.06
    à¤Ĥà¤ľ
    -0.06
    ÑĢоÑģ
    -0.06
    POSITIVE LOGITS
    information
    0.07
     information
    0.07
    pard
    0.07
    related
    0.07
    abcdefghijkl
    0.07
    dete
    0.07
    _information
    0.06
     bil
    0.06
    About
    0.06
    RD
    0.06
    Activations Density 0.012%

    No Known Activations