© 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. 62329
    Prev
    Next
    INDEX
    Explanations

    terms related to military actions and strategies

    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
    andal
    -0.07
     Universe
    -0.07
     Bour
    -0.07
    yles
    -0.06
     пеÑĢеп
    -0.06
    าà¸ģร
    -0.06
    SearchParams
    -0.06
    ORS
    -0.06
    fty
    -0.06
    è¡ĵ
    -0.06
    POSITIVE LOGITS
     nuclear
    0.09
     surviv
    0.09
     Nuclear
    0.08
    æł¸
    0.08
    uclear
    0.07
     EMP
    0.07
     launch
    0.07
    EMP
    0.07
    atch
    0.07
    legen
    0.06
    Activations Density 0.018%

    No Known Activations