© 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. 5891
    Prev
    Next
    INDEX
    Explanations

    statements regarding actions and interactions

    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
    olf
    -0.07
    iesel
    -0.06
    andre
    -0.06
     Kauf
    -0.06
    zm
    -0.06
    ronics
    -0.06
    .instructions
    -0.06
    ç«Ł
    -0.06
    lsi
    -0.06
    otos
    -0.06
    POSITIVE LOGITS
    orz
    0.07
    .ArgumentParser
    0.07
    baum
    0.06
     because
    0.06
    uggle
    0.06
    áºł
    0.06
     although
    0.06
    WithMany
    0.06
    adin
    0.06
    iri
    0.06
    Activations Density 0.043%

    No Known Activations