© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shrug" and its variations

    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
    ibr
    -0.07
    iedad
    -0.06
    onet
    -0.06
     Fav
    -0.06
    iej
    -0.06
     unmarried
    -0.06
    -ÑĤо
    -0.06
    acob
    -0.06
    rac
    -0.06
    anic
    -0.06
    POSITIVE LOGITS
    asti
    0.07
    ãĥ³ãĥĨãĤ£
    0.07
     Shr
    0.06
    astle
    0.06
    èŀº
    0.06
    aders
    0.06
    GGLE
    0.06
     danmark
    0.06
    翼
    0.06
    shr
    0.06
    Activations Density 0.009%

    No Known Activations