© 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 EvalsExportsinterp-engineNEWAPI 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. 2704
    Prev
    Next
    INDEX
    Explanations

    military ranks and related positions

    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
    ambi
    -0.09
    imens
    -0.07
     banka
    -0.07
     reinforcements
    -0.07
    олниÑĤелÑĮ
    -0.07
    /GPL
    -0.07
    ãĤŀ
    -0.07
    atoire
    -0.07
     SWAT
    -0.07
    ì£
    -0.07
    POSITIVE LOGITS
     military
    0.11
     Military
    0.10
     rank
    0.10
     officer
    0.09
     command
    0.09
     training
    0.09
     officers
    0.08
    Rank
    0.08
     Rank
    0.08
    Military
    0.08
    Activations Density 0.395%

    No Known Activations