© 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. 31487
    Prev
    Next
    INDEX
    Explanations

    mentions of military forces and organizations

    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
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    zo
    -0.07
    oku
    -0.07
    vy
    -0.06
    sian
    -0.06
    éIJĺ
    -0.06
    lamaz
    -0.06
    _ONCE
    -0.06
    aney
    -0.06
     himself
    -0.06
    POSITIVE LOGITS
    (JS
    0.06
    /lg
    0.06
    splash
    0.06
    -US
    0.06
    /pol
    0.06
    oton
    0.06
     crest
    0.06
    Enlarge
    0.06
    é§IJ
    0.06
    975
    0.05
    Activations Density 0.041%

    No Known Activations