© 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. 5192
    Prev
    Next
    INDEX
    Explanations

    instances of 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
    ikut
    -0.07
    endar
    -0.06
     spect
    -0.06
    ecies
    -0.06
     option
    -0.06
    QR
    -0.06
    arging
    -0.06
    اÙĪر
    -0.06
    isecond
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
     purpose
    0.09
     Purpose
    0.09
    purpose
    0.08
    /basic
    0.07
    alone
    0.07
    .scalablytyped
    0.07
    éĿ©
    0.07
    oden
    0.07
    BACKGROUND
    0.07
    -original
    0.06
    Activations Density 0.065%

    No Known Activations