© 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. 63114
    Prev
    Next
    INDEX
    Explanations

    instructions for preparing ingredients in a recipe

    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
     ejac
    -0.07
     Fruit
    -0.06
    amel
    -0.06
    Coffee
    -0.06
    antity
    -0.06
    coffee
    -0.06
     cotton
    -0.06
     coffee
    -0.06
     grape
    -0.06
    tran
    -0.06
    POSITIVE LOGITS
    osen
    0.08
    διο
    0.07
     bulb
    0.07
    Į¨
    0.07
    Matchers
    0.07
    panic
    0.06
    jon
    0.06
    ScrollPane
    0.06
     rad
    0.06
     swe
    0.06
    Activations Density 0.077%

    No Known Activations