© 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. 123501
    Prev
    Next
    INDEX
    Explanations

    references to violent incidents, particularly mass shootings and their locations

    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
    inge
    -0.07
     Kid
    -0.07
    aris
    -0.06
    liga
    -0.06
    arias
    -0.06
    .Glide
    -0.06
    infos
    -0.06
     wol
    -0.06
    Ñīин
    -0.06
     mechan
    -0.06
    POSITIVE LOGITS
     earlier
    0.07
     Willi
    0.07
     involving
    0.07
    .printStackTrace
    0.06
     Forrest
    0.06
    /rfc
    0.06
    thren
    0.06
     Rek
    0.06
     recent
    0.06
     happening
    0.06
    Activations Density 0.017%

    No Known Activations