© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74479
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" and its frequency in various contexts

    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
    ÑĨов
    -0.07
    etooth
    -0.06
     Ellison
    -0.06
    ãģ¡ãģ¯
    -0.06
    imdi
    -0.06
    -ass
    -0.06
     *</
    -0.06
    -Ass
    -0.06
     seedu
    -0.06
    ãģªãģĮãĤī
    -0.06
    POSITIVE LOGITS
    IDD
    0.07
    olle
    0.07
    yb
    0.07
    isman
    0.06
    ches
    0.06
    yre
    0.06
     Conversely
    0.06
    riba
    0.06
    ear
    0.06
    bole
    0.06
    Activations Density 0.054%

    No Known Activations