© 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. 73828
    Prev
    Next
    INDEX
    Explanations

    references to women's representation and participation in politics

    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
    uhn
    -0.07
    ENTE
    -0.07
    _CSR
    -0.06
    ariat
    -0.06
    ëĵ
    -0.06
    ÑĤÑİ
    -0.06
    hausen
    -0.06
    airs
    -0.06
    аÑĩе
    -0.06
     Slider
    -0.06
    POSITIVE LOGITS
     representation
    0.07
     Represent
    0.07
     Representation
    0.07
    ersion
    0.07
     swearing
    0.06
    idal
    0.06
    Representation
    0.06
    representation
    0.06
    utan
    0.06
     introdu
    0.06
    Activations Density 0.004%

    No Known Activations