© 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. 53740
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and connections

    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
    yr
    -0.07
    ually
    -0.06
     guaranteed
    -0.06
    ienia
    -0.06
    Ç
    -0.06
    agu
    -0.06
    urs
    -0.06
    plate
    -0.06
    yn
    -0.06
     strapon
    -0.06
    POSITIVE LOGITS
    $MESS
    0.08
    лиÑĪком
    0.07
    rika
    0.07
    rush
    0.07
    alet
    0.07
    âĻ¡
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    gov
    0.07
    $LANG
    0.07
    емо
    0.07
    Activations Density 0.054%

    No Known Activations