© 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. 88785
    Prev
    Next
    INDEX
    Explanations

    references to Jewish history and diaspora

    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
    irie
    -0.07
    uyu
    -0.07
    855
    -0.06
    agnost
    -0.06
    ace
    -0.06
    ằng
    -0.06
    .staff
    -0.06
     Ont
    -0.06
    ACHINE
    -0.06
    quette
    -0.06
    POSITIVE LOGITS
    Jer
    0.07
    ÙĪرش
    0.07
    roker
    0.07
    ilik
    0.06
     Jerusalem
    0.06
    typings
    0.06
     Trigger
    0.06
     triggered
    0.06
     rabbit
    0.06
    ulet
    0.06
    Activations Density 0.009%

    No Known Activations