© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107452
    Prev
    Next
    INDEX
    Explanations

    negative or critical sentiments regarding governance and societal issues

    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
    mî
    -0.07
     penet
    -0.06
    ÑĢий
    -0.06
     downfall
    -0.06
    pcl
    -0.06
    lech
    -0.06
     ê·¼
    -0.06
     chem
    -0.06
    inqu
    -0.06
     fat
    -0.06
    POSITIVE LOGITS
    对æĸ¹
    0.08
    sdale
    0.08
    æħĭ
    0.07
    agements
    0.06
    -actions
    0.06
     antics
    0.06
    æĢģ
    0.06
     Resorts
    0.06
     lately
    0.06
     Resort
    0.06
    Activations Density 0.033%

    No Known Activations