© 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. 18619
    Prev
    Next
    INDEX
    Explanations

    references to songwriting and music creation

    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
    AGMA
    -0.08
     Oro
    -0.07
    astes
    -0.07
    å·»
    -0.07
    apiro
    -0.06
    akit
    -0.06
    ramer
    -0.06
    çIJ³
    -0.06
    htar
    -0.06
    -www
    -0.06
    POSITIVE LOGITS
     inspir
    0.08
    pest
    0.07
     ideas
    0.07
    oggle
    0.06
    indi
    0.06
     gest
    0.06
    Į¨
    0.06
    زÙĦ
    0.06
     genesis
    0.06
     inspiration
    0.06
    Activations Density 0.023%

    No Known Activations