© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 27874
    Prev
    Next
    INDEX
    Explanations

    elements related to social media interactions and URLs

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

    Links or references to social media posts (usually Twitter) where shortened URLs or IDs appear at the end, often followed by quotation marks that indicate the start or end of quoted content. These markers typically appear at the transition points between quoted text and commentary.

    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
     Lam
    -0.06
    eah
    -0.06
     Brick
    -0.06
     Todd
    -0.06
    insk
    -0.06
    ÃĹ↵↵
    -0.06
     peppers
    -0.06
    nees
    -0.06
     Loft
    -0.06
    å¥Ī
    -0.06
    POSITIVE LOGITS
    Reply
    0.09
    Ã¤ÃŁ
    0.07
    coat
    0.07
     thunder
    0.07
     reply
    0.07
    reply
    0.07
     mildly
    0.06
    rip
    0.06
    ỡ
    0.06
     Reply
    0.06
    Activations Density 0.085%

    No Known Activations