© 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. 75698
    Prev
    Next
    INDEX
    Explanations

    terms related to media influence and economic control

    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
    кеÑĤ
    -0.06
    imuth
    -0.06
    urus
    -0.06
    utron
    -0.06
    ابر
    -0.06
    кин
    -0.05
    kses
    -0.05
     fre
    -0.05
     Surf
    -0.05
     ale
    -0.05
    POSITIVE LOGITS
    imestone
    0.07
    ãĤ¤ãĥī
    0.07
    tod
    0.07
     exclusively
    0.07
    readcr
    0.07
    ª
    0.06
    olland
    0.06
    дÑĸл
    0.06
     Owned
    0.06
    \Id
    0.06
    Activations Density 0.019%

    No Known Activations