© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69168
    Prev
    Next
    INDEX
    Explanations

    phrases related to military strength and capabilities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    andal
    -0.07
     colorWith
    -0.06
     carc
    -0.06
    aida
    -0.06
    wear
    -0.06
    dao
    -0.06
    agi
    -0.06
    ç¹Ķ
    -0.06
    pecting
    -0.06
    ê·¼
    -0.06
    POSITIVE LOGITS
     capability
    0.08
     acquiring
    0.07
     capabilities
    0.07
    Capabilities
    0.07
     technology
    0.07
     fiss
    0.07
    technology
    0.07
    нез
    0.07
    capability
    0.07
     nuclear
    0.07
    Activations Density 0.028%

    No Known Activations