© 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. 17-LLAMASCOPE-RES-131K
    11. 16053
    Prev
    Next
    INDEX
    Explanations

    phrases related to political accountability and the consequences of leadership decisions

    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
    ien
    -0.07
    FIXME
    -0.06
    814
    -0.06
     Statistics
    -0.06
    ascus
    -0.06
    _stats
    -0.06
     statistics
    -0.06
    è¿Ļæł·çļĦ
    -0.06
    hp
    -0.06
    istory
    -0.06
    POSITIVE LOGITS
    uml
    0.07
    oloj
    0.07
    andon
    0.06
    ££
    0.06
     æĬķ稿
    0.06
    åķĬåķĬ
    0.06
    vince
    0.06
    kening
    0.06
    iqué
    0.06
    reck
    0.06
    Activations Density 0.002%

    No Known Activations