© 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. 17-LLAMASCOPE-RES-131K
    6. 40961
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and administrative roles

    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
     seen
    -0.08
     Seen
    -0.06
     observed
    -0.06
    ooke
    -0.06
     Gib
    -0.06
     observation
    -0.06
    chwitz
    -0.06
    asca
    -0.06
    rometer
    -0.06
     popped
    -0.05
    POSITIVE LOGITS
    ViewById
    0.08
    allen
    0.08
    317
    0.08
    ered
    0.07
    Ĥæķ°
    0.07
    launcher
    0.07
     nowhere
    0.07
     willing
    0.07
    amental
    0.07
    Contours
    0.07
    Activations Density 0.177%

    No Known Activations