© 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. 80658
    Prev
    Next
    INDEX
    Explanations

    information related to travel itineraries and logistics

    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
    .archive
    -0.07
    imit
    -0.06
    itar
    -0.06
    одо
    -0.06
    лаÑĤÑĭ
    -0.06
    Arguments
    -0.06
     ed
    -0.06
     Levy
    -0.06
     genie
    -0.06
     Roo
    -0.05
    POSITIVE LOGITS
     customs
    0.08
    ToLocal
    0.07
    osphere
    0.07
     taxi
    0.07
     Customs
    0.07
    ÑĢазÑĥ
    0.07
    bil
    0.07
     immigration
    0.07
     immediately
    0.07
    airport
    0.06
    Activations Density 0.025%

    No Known Activations