© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95337
    Prev
    Next
    INDEX
    Explanations

    references to questioning and decision-making 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
    ieber
    -0.08
    ench
    -0.06
    All
    -0.06
    tr
    -0.05
     Meadows
    -0.05
    ti
    -0.05
    umble
    -0.05
    enko
    -0.05
    tein
    -0.05
    WI
    -0.05
    POSITIVE LOGITS
    ãĤ¿ãĥ³
    0.09
    enville
    0.08
    ÑĢг
    0.08
     discre
    0.07
     ux
    0.07
    FLT
    0.07
    Ïģκε
    0.07
    uyên
    0.07
    kest
    0.07
    AttributeValue
    0.07
    Activations Density 0.119%

    No Known Activations