© 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. 38350
    Prev
    Next
    INDEX
    Explanations

    references to travel and booking flights

    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
    êu
    -0.07
    ugar
    -0.07
    cerpt
    -0.07
    kontakte
    -0.07
    raith
    -0.07
    inke
    -0.07
    reta
    -0.06
    软
    -0.06
    vier
    -0.06
    æ
    -0.06
    POSITIVE LOGITS
    irie
    0.07
     autof
    0.07
     Kür
    0.07
     èĪ
    0.06
    .interfaces
    0.06
    ÑĢоÑĩ
    0.06
     Trident
    0.06
    úp
    0.06
    elman
    0.06
    Ïĥμα
    0.06
    Activations Density 0.006%

    No Known Activations