© 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. 15-LLAMASCOPE-RES-131K
    6. 454
    Prev
    Next
    INDEX
    Explanations

    terms related to authority and governance, often in a political context

    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
    337
    -0.08
    ish
    -0.06
    [to
    -0.06
    quest
    -0.06
    357
    -0.06
     quoi
    -0.06
    erd
    -0.05
    ITTE
    -0.05
    ong
    -0.05
     Meadows
    -0.05
    POSITIVE LOGITS
    xes
    0.08
    gow
    0.08
    зÑĮ
    0.07
    erland
    0.07
    vik
    0.07
    viz
    0.07
    ipes
    0.07
    ARS
    0.07
    sted
    0.07
    elay
    0.07
    Activations Density 0.004%

    No Known Activations