© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    words indicating comparison or distinction between entities

    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
    èį
    -0.07
    ennon
    -0.06
    اÙĦا
    -0.06
    ERCHANT
    -0.06
    Ñģм
    -0.06
    arna
    -0.06
    Ral
    -0.06
     Thá»ķ
    -0.06
     ÑģкладÑĥ
    -0.06
     !$
    -0.06
    POSITIVE LOGITS
     than
    0.09
    _than
    0.07
    Than
    0.07
     THAN
    0.07
     Than
    0.06
    Bindable
    0.06
     Salt
    0.06
    than
    0.06
    937
    0.06
     quam
    0.06
    Activations Density 0.002%

    No Known Activations