© 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. 91643
    Prev
    Next
    INDEX
    Explanations

    terms related to programming assertions and testing frameworks

    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
    ắn
    -0.07
    atures
    -0.06
     slow
    -0.06
    zá
    -0.06
     East
    -0.06
    ude
    -0.06
     Slow
    -0.06
    lej
    -0.06
    uers
    -0.06
    ently
    -0.06
    POSITIVE LOGITS
    .assertThat
    0.07
    memberOf
    0.07
    IPA
    0.06
    >(()
    0.06
    лаб
    0.06
    êµ°
    0.06
    SKI
    0.06
    irst
    0.06
    forge
    0.06
     Kurd
    0.06
    Activations Density 0.000%

    No Known Activations