© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107593
    Prev
    Next
    INDEX
    Explanations

    references to chat room functionalities and user account management

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

    Text that appears in user interfaces indicating system status, account information, or action confirmations, often within web elements or application feedback.

    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
    reh
    -0.08
     histo
    -0.06
     Claus
    -0.06
    alama
    -0.06
     yana
    -0.06
    пÑĢиклад
    -0.06
    agg
    -0.06
    baum
    -0.06
    ivan
    -0.06
     oneself
    -0.06
    POSITIVE LOGITS
    æĤ¨çļĦ
    0.09
     your
    0.08
    ä½łçļĦ
    0.08
    Your
    0.08
     Your
    0.07
    your
    0.07
     ваÑĪ
    0.07
     YOUR
    0.07
    esta
    0.06
    angs
    0.06
    Activations Density 0.006%

    No Known Activations