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

    Neuronpedia

    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. 41116
    Prev
    Next
    INDEX
    Explanations

    instances of the definite 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
     Beste
    -0.07
    اÙħÙĩ
    -0.07
    бÑĢа
    -0.06
    нÑĮ
    -0.06
    _WRAP
    -0.06
    ̧
    -0.06
    znam
    -0.06
    ÑĦи
    -0.06
     Cunning
    -0.06
    upo
    -0.06
    POSITIVE LOGITS
    iki
    0.07
    isphere
    0.07
    ighb
    0.07
    ÃŃsticas
    0.06
    aur
    0.06
     McKin
    0.06
    omanip
    0.06
    ãĥĸãĥ«
    0.06
     Rooney
    0.06
    cken
    0.06
    Activations Density 0.023%

    No Known Activations