© 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 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. 97100
    Prev
    Next
    INDEX
    Explanations

    references to government and its various aspects

    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
    æľŁ
    -0.07
    ocha
    -0.07
    keley
    -0.07
    aign
    -0.07
    ublish
    -0.07
    erin
    -0.07
    ire
    -0.07
     æľŁ
    -0.07
    orious
    -0.06
    änn
    -0.06
    POSITIVE LOGITS
     our
    0.06
    se
    0.06
    fillna
    0.06
    ystem
    0.06
    ESH
    0.06
    our
    0.06
    %č↵
    0.06
    ystems
    0.06
    'url
    0.06
     hyper
    0.05
    Activations Density 0.035%

    No Known Activations