© 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. 53728
    Prev
    Next
    INDEX
    Explanations

    references to inspiration and influence in creative works

    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
    .mm
    -0.07
    okin
    -0.06
    ä¼´
    -0.06
    ammen
    -0.06
    nas
    -0.06
    eware
    -0.06
     Buccane
    -0.06
    empo
    -0.06
    Beans
    -0.06
    zn
    -0.06
    POSITIVE LOGITS
     inspiration
    0.08
     inspir
    0.08
    ATAB
    0.07
    Ymd
    0.07
    enty
    0.07
    older
    0.07
     Inspiration
    0.06
     kalk
    0.06
     cogn
    0.06
    gan
    0.06
    Activations Density 0.025%

    No Known Activations