© 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. 118814
    Prev
    Next
    INDEX
    Explanations

    terms related to the Supreme Court

    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
    tings
    -0.07
    جÙĪ
    -0.07
    lish
    -0.06
     Rafael
    -0.06
    si
    -0.06
    unma
    -0.06
    ÑĩаÑĤ
    -0.06
    jee
    -0.06
    à¥įरव
    -0.06
    çak
    -0.06
    POSITIVE LOGITS
    uros
    0.07
    iy
    0.07
    ardin
    0.06
    imizer
    0.06
     irony
    0.06
    etable
    0.06
    artz
    0.06
    aller
    0.06
    SSION
    0.06
    anners
    0.06
    Activations Density 0.013%

    No Known Activations