© 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. 42546
    Prev
    Next
    INDEX
    Explanations

    programming-related comparisons and conditions

    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
    uche
    -0.08
    вол
    -0.07
    anga
    -0.07
    NECT
    -0.07
    اÙħÛĮÙĨ
    -0.07
    cone
    -0.07
    raž
    -0.07
     NONE
    -0.07
    .FontStyle
    -0.06
    morgan
    -0.06
    POSITIVE LOGITS
    ncia
    0.07
    oppins
    0.06
    ortal
    0.06
     Pioneer
    0.06
    uggy
    0.06
    ses
    0.06
     count
    0.05
    lug
    0.05
    ìĦł
    0.05
     counter
    0.05
    Activations Density 0.008%

    No Known Activations