© 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 EvalsExportsinterp-engineNEWAPI 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. 5354
    Prev
    Next
    INDEX
    Explanations

    instances of the article "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
    &view
    -0.07
     thing
    -0.07
    fone
    -0.06
    ÑĨе
    -0.06
    zag
    -0.06
    zych
    -0.06
    ighton
    -0.06
    aits
    -0.06
    æĺĮ
    -0.06
    peak
    -0.06
    POSITIVE LOGITS
     final
    0.09
    ctal
    0.07
     orient
    0.06
    OSH
    0.06
     tim
    0.06
    iba
    0.06
    ttl
    0.06
    oref
    0.06
    dll
    0.06
    tim
    0.06
    Activations Density 0.015%

    No Known Activations