© 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. 104139
    Prev
    Next
    INDEX
    Explanations

    mentions of tickets for sporting events

    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
    اÙħÛĮÙĨ
    -0.07
    agrams
    -0.07
    anol
    -0.07
    agher
    -0.07
    eron
    -0.07
    ertainment
    -0.07
    ool
    -0.07
    imar
    -0.07
    zos
    -0.06
    urgy
    -0.06
    POSITIVE LOGITS
    stad
    0.06
    AUSE
    0.06
     shorthand
    0.06
    ONSE
    0.06
     Fallon
    0.06
     Meyer
    0.06
    Lite
    0.06
    xdd
    0.06
     Sever
    0.06
    uisse
    0.05
    Activations Density 0.000%

    No Known Activations