© 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. 39488
    Prev
    Next
    INDEX
    Explanations

    references to drone strikes and their consequences in military contexts

    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
    MBER
    -0.05
    astr
    -0.05
     Cli
    -0.05
    rag
    -0.05
    Injected
    -0.05
    лаг
    -0.05
     xsi
    -0.05
    èµ·ãģĵ
    -0.05
     Orange
    -0.05
    yz
    -0.05
    POSITIVE LOGITS
     Reaper
    0.08
    strand
    0.08
    remote
    0.07
    utomation
    0.07
    issan
    0.07
    kill
    0.07
    Remote
    0.07
     drone
    0.07
     remote
    0.07
     kill
    0.07
    Activations Density 0.023%

    No Known Activations