© 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. 42794
    Prev
    Next
    INDEX
    Explanations

    references to queer themes and protectiveness over sexual purity

    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
    .scalablytyped
    -0.10
    ázd
    -0.07
    erdale
    -0.07
    dlg
    -0.07
     èĢ
    -0.07
    eniz
    -0.07
    VML
    -0.07
    ityEngine
    -0.07
    _Framework
    -0.07
     addCriterion
    -0.07
    POSITIVE LOGITS
     early
    0.07
    ape
    0.07
    early
    0.06
    itzer
    0.06
    nock
    0.06
     tape
    0.06
     earlier
    0.06
    rick
    0.06
    acco
    0.06
     Hall
    0.06
    Activations Density 0.054%

    No Known Activations