© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77034
    Prev
    Next
    INDEX
    Explanations

    phrases related to military spending and defense matters

    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
    ednou
    -0.07
    cai
    -0.07
     ApplicationController
    -0.06
    ulp
    -0.06
    eland
    -0.06
     getattr
    -0.06
    achine
    -0.06
    gram
    -0.06
    chl
    -0.06
     شخصÙĬØ©
    -0.06
    POSITIVE LOGITS
     military
    0.07
     Defence
    0.07
     Military
    0.06
    ẫn
    0.06
    oints
    0.06
     DEF
    0.06
     defence
    0.06
    Military
    0.06
    Īëĭ¤
    0.06
     Defense
    0.06
    Activations Density 0.003%

    No Known Activations