© 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. 69011
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" in various contexts

    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
    441
    -0.06
    eda
    -0.05
    eto
    -0.05
    nez
    -0.05
    ez
    -0.05
     gardens
    -0.05
    âĢ¦↵
    -0.05
    qu
    -0.05
    >
    -0.05
    ..
    -0.05
    POSITIVE LOGITS
    Filed
    0.08
    ENDOR
    0.08
    iegel
    0.08
    eyle
    0.07
    ebe
    0.07
    edor
    0.07
    _icall
    0.07
     addCriterion
    0.07
    /goto
    0.07
    _Lean
    0.07
    Activations Density 0.019%

    No Known Activations