© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42429
    Prev
    Next
    INDEX
    Explanations

    instances of political conflict and opposition

    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
    anst
    -0.08
    üçük
    -0.07
    /INFO
    -0.07
     ÙħÙĦÛĮ
    -0.07
    ayne
    -0.07
    gebn
    -0.07
    ollapse
    -0.07
    .googlecode
    -0.07
    iske
    -0.07
    utsch
    -0.07
    POSITIVE LOGITS
    obj
    0.09
     objections
    0.08
     objection
    0.07
     powerful
    0.07
     resistance
    0.07
     obj
    0.07
     key
    0.06
    æĿ¥èĩª
    0.06
     obstruction
    0.06
     obstacles
    0.06
    Activations Density 0.029%

    No Known Activations