© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    questions related to influences and inspirations 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
    addock
    -0.08
    leur
    -0.07
    ister
    -0.06
    addtogroup
    -0.06
    й
    -0.06
     vlast
    -0.06
     companion
    -0.06
    andalone
    -0.06
    defgroup
    -0.06
    letic
    -0.06
    POSITIVE LOGITS
     influences
    0.16
     influence
    0.15
     Influence
    0.14
     inspiration
    0.12
     Influ
    0.12
    å½±éŁ¿
    0.12
     influenced
    0.11
     ìĺģíĸ¥ìĿĦ
    0.11
     inspir
    0.11
     influencers
    0.10
    Activations Density 0.070%

    No Known Activations