© 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. 108843
    Prev
    Next
    INDEX
    Explanations

    references to "the" followed by significant descriptors or entities, particularly in contexts related to comparison or classification

    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
    hazi
    -0.07
    nox
    -0.07
    amburg
    -0.06
    owel
    -0.06
     both
    -0.06
    GS
    -0.06
    iez
    -0.06
     coolest
    -0.06
    imuth
    -0.06
    bas
    -0.06
    POSITIVE LOGITS
     anymore
    0.14
     necessarily
    0.14
     nor
    0.10
    nor
    0.07
     usual
    0.06
     Nor
    0.06
    ecessarily
    0.06
    ocha
    0.06
     slightest
    0.06
     nữa
    0.06
    Activations Density 0.016%

    No Known Activations