© 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. 73322
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental or organizational structures and meetings

    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
    acey
    -0.07
     neust
    -0.07
    eyn
    -0.06
    LATED
    -0.06
    ¼åIJĪ
    -0.06
    grave
    -0.06
    olit
    -0.06
    ÙĬات
    -0.06
    .matcher
    -0.06
    opo
    -0.06
    POSITIVE LOGITS
     held
    0.09
    held
    0.09
    -held
    0.08
     Held
    0.07
    à¹ĥหà¸į
    0.07
    IENT
    0.07
    noc
    0.07
    rooms
    0.07
     annual
    0.06
     voting
    0.06
    Activations Density 0.015%

    No Known Activations