© 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. 87397
    Prev
    Next
    INDEX
    Explanations

    terms related to military operations and their impacts

    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
    PlainText
    -0.07
    بس
    -0.06
    reece
    -0.06
    PLE
    -0.06
     رÙħ
    -0.06
    _ONCE
    -0.06
    LEEP
    -0.06
    .features
    -0.06
     doz
    -0.06
     Roose
    -0.06
    POSITIVE LOGITS
    oins
    0.07
    ainment
    0.06
     embed
    0.06
     mop
    0.06
    857
    0.06
    ona
    0.06
    embedding
    0.06
    inning
    0.06
     rede
    0.06
    iona
    0.06
    Activations Density 0.028%

    No Known Activations