© 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. 38898
    Prev
    Next
    INDEX
    Explanations

    military actions and the context surrounding warfare

    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
    andle
    -0.09
    atoire
    -0.07
    iveau
    -0.07
    ToWorld
    -0.07
    onis
    -0.07
    itti
    -0.06
    Asia
    -0.06
    Guard
    -0.06
     DISPATCH
    -0.06
     Glow
    -0.06
    POSITIVE LOGITS
     opposing
    0.09
     enemy
    0.09
     loyal
    0.09
     aligned
    0.08
     allied
    0.08
     opponent
    0.08
     Coalition
    0.08
     allegiance
    0.07
     Alliance
    0.07
     Äijá»ĭch
    0.07
    Activations Density 0.135%

    No Known Activations