© 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. 87032
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates and new information

    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
    身份
    -0.07
    .showMessage
    -0.07
    eldon
    -0.07
    ÑģпÑĸлÑĮ
    -0.07
    .kode
    -0.06
    loh
    -0.06
    891
    -0.06
    393
    -0.06
    èĬĻ
    -0.06
    æ´¾
    -0.06
    POSITIVE LOGITS
     update
    0.09
     updates
    0.08
     updating
    0.07
     updated
    0.07
     Update
    0.07
     additions
    0.07
    enever
    0.07
    updates
    0.07
     added
    0.07
     adding
    0.06
    Activations Density 0.013%

    No Known Activations