© 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. 116366
    Prev
    Next
    INDEX
    Explanations

    references to musical bands and their activities

    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
    oose
    -0.08
    Celebr
    -0.07
    annah
    -0.07
    allery
    -0.07
    бÑĢа
    -0.07
    Exam
    -0.06
     Celebration
    -0.06
    uteur
    -0.06
    agher
    -0.06
    Inspectable
    -0.06
    POSITIVE LOGITS
    lei
    0.07
     feature
    0.06
     privilege
    0.06
     appearance
    0.06
     Pearson
    0.06
     features
    0.06
    atron
    0.06
     Priv
    0.06
    ino
    0.06
     slots
    0.06
    Activations Density 0.014%

    No Known Activations