© 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. 41253
    Prev
    Next
    INDEX
    Explanations

    elements related to chatroom interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML code fragments from a web-based XMPP/Jabber chat client interface, focusing on structural elements, attributes, and chat-related terminology.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    AAF
    -0.07
    алов
    -0.07
     иÑģполн
    -0.07
    thouse
    -0.06
    resa
    -0.06
    /Gate
    -0.06
    /car
    -0.06
     Zip
    -0.06
    ifact
    -0.06
    panse
    -0.06
    POSITIVE LOGITS
     chat
    0.11
    chat
    0.10
     Chat
    0.10
    CHAT
    0.09
    -chat
    0.08
     chats
    0.08
    (chat
    0.08
    Chat
    0.08
    (Chat
    0.08
    _chat
    0.07
    Activations Density 0.060%

    No Known Activations