© 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. 17-LLAMASCOPE-RES-131K
    11. 86035
    Prev
    Next
    INDEX
    Explanations

    references to oil and its cultural or societal impacts

    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
    Statics
    -0.08
    ηÏĤ
    -0.08
    TPL
    -0.08
    .TryParse
    -0.07
    /gtest
    -0.07
    onomous
    -0.07
    chez
    -0.07
    czy
    -0.07
    PROCESS
    -0.07
    .gwt
    -0.07
    POSITIVE LOGITS
     simultaneously
    0.06
    Âł
    0.06
     labor
    0.06
    anto
    0.06
    enson
    0.06
    dden
    0.06
     Rockefeller
    0.06
    196
    0.06
     labour
    0.06
     trop
    0.06
    Activations Density 0.014%

    No Known Activations