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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41197
    Prev
    Next
    INDEX
    Explanations

    references to historical or legendary figures in leadership and 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
    Bomb
    -0.07
    รม
    -0.07
    bomb
    -0.07
    寿
    -0.07
    imals
    -0.07
    afen
    -0.07
    _CPP
    -0.07
     Bomb
    -0.07
    à¸ģรรม
    -0.07
    chied
    -0.07
    POSITIVE LOGITS
     battle
    0.08
     fighting
    0.08
     victories
    0.07
     victory
    0.07
     military
    0.07
     battlefield
    0.07
     prowess
    0.07
     leadership
    0.07
     fight
    0.07
     chiến
    0.07
    Activations Density 0.066%

    No Known Activations