© 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. 70548
    Prev
    Next
    INDEX
    Explanations

    the word "on" followed by numbers, indicating dates or references to time

    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
    raft
    -0.06
    .str
    -0.06
    oven
    -0.06
    apur
    -0.06
    938
    -0.06
    orem
    -0.06
    craft
    -0.06
     chuck
    -0.05
    anders
    -0.05
     feel
    -0.05
    POSITIVE LOGITS
    ICODE
    0.07
    dü
    0.07
    تباط
    0.07
    loadModel
    0.07
    ?option
    0.07
    heimer
    0.07
    ìĿ´íĦ°
    0.06
    à¸ļาย
    0.06
    ustomed
    0.06
    lashes
    0.06
    Activations Density 0.002%

    No Known Activations