© 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. 126082
    Prev
    Next
    INDEX
    Explanations

    the name "Jacques" and variations of the word "ques"

    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
    nell
    -0.07
    Ìĥ
    -0.07
    sah
    -0.07
    ounge
    -0.07
    ply
    -0.07
    etik
    -0.07
    .strict
    -0.07
    akter
    -0.06
    ease
    -0.06
    ccion
    -0.06
    POSITIVE LOGITS
     Zum
    0.07
    owi
    0.06
    owitz
    0.06
     Batt
    0.06
     matter
    0.06
    ie
    0.06
    erk
    0.06
     Kral
    0.06
    mith
    0.06
    lesi
    0.05
    Activations Density 0.005%

    No Known Activations