© 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. 89867
    Prev
    Next
    INDEX
    Explanations

    phrases related to airport and travel 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
    fell
    -0.06
    ala
    -0.06
    å½
    -0.06
    awan
    -0.06
     transport
    -0.06
    teki
    -0.06
    inois
    -0.06
     reign
    -0.06
    949
    -0.06
     imported
    -0.06
    POSITIVE LOGITS
    indle
    0.08
     boarding
    0.08
     Depart
    0.07
     baggage
    0.07
    帯
    0.07
    reeze
    0.07
     Suites
    0.06
     terminal
    0.06
     ninh
    0.06
     passengers
    0.06
    Activations Density 0.006%

    No Known Activations