© 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. 96206
    Prev
    Next
    INDEX
    Explanations

    references to a booking or reservation system

    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
    enco
    -0.09
     Ñħод
    -0.07
    .dk
    -0.07
    aleigh
    -0.07
    estone
    -0.07
     Cumberland
    -0.07
    aura
    -0.07
    Aura
    -0.07
    uncated
    -0.07
    omap
    -0.07
    POSITIVE LOGITS
    éro
    0.06
     VÅ©
    0.06
     inters
    0.05
     ÙħØ«ÙĦا
    0.05
     Urs
    0.05
     Artem
    0.05
     tô
    0.05
    982
    0.05
    513
    0.05
    å²
    0.05
    Activations Density 0.000%

    No Known Activations