© 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. 42498
    Prev
    Next
    INDEX
    Explanations

    references to characters and relationships in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     addCriterion
    -0.09
    UNUSED
    -0.09
    enburg
    -0.08
    isoner
    -0.08
    orgia
    -0.08
    .Designer
    -0.07
    warts
    -0.07
     gratuitement
    -0.07
    bob
    -0.07
    _CPP
    -0.07
    POSITIVE LOGITS
     Introduced
    0.06
     a
    0.06
     custody
    0.06
     new
    0.06
     "
    0.06
     recurring
    0.06
     complications
    0.05
     schem
    0.05
     per
    0.05
     opposite
    0.05
    Activations Density 0.006%

    No Known Activations