© 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. 29791
    Prev
    Next
    INDEX
    Explanations

    references to submarines and naval military operations

    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
    hek
    -0.07
    arton
    -0.06
    é£ŀ
    -0.06
     useForm
    -0.06
    reeze
    -0.06
     Conc
    -0.06
    .Cross
    -0.06
    inha
    -0.06
    asename
    -0.06
    iman
    -0.06
    POSITIVE LOGITS
     submarines
    0.07
    fish
    0.07
     submarine
    0.07
    HandlerContext
    0.07
     compressed
    0.07
     bubbles
    0.07
     reversible
    0.06
    ần
    0.06
     swim
    0.06
     fish
    0.06
    Activations Density 0.009%

    No Known Activations