© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127517
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ingo
    -0.06
     hall
    -0.06
     associated
    -0.06
    aper
    -0.06
     Dame
    -0.06
     types
    -0.06
     equally
    -0.06
     Guth
    -0.06
     halls
    -0.06
    lander
    -0.06
    POSITIVE LOGITS
     Piece
    0.07
    'gc
    0.07
    ogne
    0.07
    acement
    0.07
    orizontal
    0.07
    درÛĮ
    0.07
     vess
    0.07
     everything
    0.07
    ernet
    0.07
    igrations
    0.06
    Activations Density 0.035%

    No Known Activations