© 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. 70878
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to dimensions, specifications, and quantities in products

    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
    utherford
    -0.07
    urg
    -0.06
    udades
    -0.06
    ster
    -0.06
    ä¸įäºĨ
    -0.06
    apt
    -0.06
    ibles
    -0.05
    itis
    -0.05
    aternity
    -0.05
     Sne
    -0.05
    POSITIVE LOGITS
    족
    0.08
    WISE
    0.07
    ftware
    0.07
     modes
    0.07
    .Serial
    0.07
    modes
    0.07
    Modes
    0.07
    енÑģ
    0.07
    éļİ
    0.07
    ánh
    0.07
    Activations Density 0.016%

    No Known Activations