© 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. 125042
    Prev
    Next
    INDEX
    Explanations

    articles and definite nouns in the text

    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
    æĺĩ
    -0.07
    iger
    -0.06
    sort
    -0.06
    enegro
    -0.06
    peri
    -0.06
    yna
    -0.06
    oned
    -0.06
    ождениÑı
    -0.06
    mar
    -0.06
    yr
    -0.06
    POSITIVE LOGITS
    że
    0.10
    icari
    0.08
    ivative
    0.07
    iaux
    0.07
    rière
    0.07
    Å¡ak
    0.07
    anke
    0.06
    .CodeAnalysis
    0.06
    ény
    0.06
    kün
    0.06
    Activations Density 0.005%

    No Known Activations