© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 75101
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements or developments in military equipment

    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
    PÅĻed
    -0.06
    ายà¹ĥà¸Ļ
    -0.06
    éĿ©
    -0.06
    mur
    -0.06
    ambre
    -0.06
    aml
    -0.06
     sap
    -0.06
    .outer
    -0.06
     militia
    -0.06
    ÚĨ
    -0.06
    POSITIVE LOGITS
    ắc
    0.06
     ÙĪÛĮر
    0.06
    itung
    0.06
     Ñģаме
    0.06
    ENARIO
    0.06
    uvre
    0.06
    jar
    0.06
     Conduct
    0.06
     conduct
    0.06
     vir
    0.06
    Activations Density 0.005%

    No Known Activations