© 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. 57458
    Prev
    Next
    INDEX
    Explanations

    references to military service and enlistment

    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
    ajs
    -0.07
    ulton
    -0.07
    visa
    -0.07
    ">//
    -0.07
    cesso
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.06
    aju
    -0.06
     Plantae
    -0.06
    igin
    -0.06
    alf
    -0.06
    POSITIVE LOGITS
     military
    0.10
     served
    0.09
     combat
    0.09
     Vietnam
    0.08
     serving
    0.08
     serve
    0.08
    comb
    0.07
     Military
    0.07
     army
    0.07
    -serving
    0.07
    Activations Density 0.039%

    No Known Activations