© 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. 96066
    Prev
    Next
    INDEX
    Explanations

    references to awards and nominations in various artistic and literary contexts

    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
     Woody
    -0.06
    åħį
    -0.06
    addle
    -0.06
    intree
    -0.06
    hop
    -0.06
    iane
    -0.06
    laps
    -0.06
    oren
    -0.06
    818
    -0.06
    ιά
    -0.06
    POSITIVE LOGITS
     for
    0.08
    .createFrom
    0.07
     forKey
    0.07
     withObject
    0.07
     regarding
    0.07
    ãĥ¼ãĥģ
    0.06
     Leban
    0.06
     itemprop
    0.06
    imity
    0.06
    Vectorizer
    0.06
    Activations Density 0.014%

    No Known Activations