© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of creation or formation

    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
    aru
    -0.07
    arb
    -0.07
    lord
    -0.07
    rien
    -0.07
    -FIRST
    -0.07
    جات
    -0.07
    cards
    -0.06
    tering
    -0.06
    inja
    -0.06
    arus
    -0.06
    POSITIVE LOGITS
     of
    0.08
     notion
    0.07
    Strict
    0.07
    658
    0.07
    æĬľ
    0.07
     idea
    0.07
    icina
    0.07
    rightness
    0.07
     notions
    0.07
    /design
    0.06
    Activations Density 0.009%

    No Known Activations