© 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. 123247
    Prev
    Next
    INDEX
    Explanations

    JavaScript/jQuery syntax and function calls

    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
     runApp
    -0.08
    illo
    -0.08
    åħĥ
    -0.07
    esti
    -0.07
    ise
    -0.07
    haft
    -0.07
    erver
    -0.07
    à¹Ĭ
    -0.07
    ãĥ©ãĤ¯
    -0.07
    usc
    -0.06
    POSITIVE LOGITS
    acre
    0.06
    ships
    0.06
    gger
    0.06
     vit
    0.06
    riel
    0.06
    475
    0.06
    ahi
    0.06
     Karlov
    0.06
    stones
    0.06
     Arb
    0.06
    Activations Density 0.003%

    No Known Activations