© 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. 81236
    Prev
    Next
    INDEX
    Explanations

    key references to Jewish identities, notable individuals, and historical contexts related to Jewish organizations

    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
     .
    -0.05
    TC
    -0.05
    pb
    -0.05
    º
    -0.05
    In
    -0.05
    unch
    -0.05
     deep
    -0.05
    astically
    -0.05
    yc
    -0.05
     pb
    -0.05
    POSITIVE LOGITS
    ̣
    0.09
    actionDate
    0.08
    âĪ¨
    0.08
    Ìģt
    0.08
    ebek
    0.08
    ADDE
    0.08
    chants
    0.07
    atedRoute
    0.07
    ImageContext
    0.07
    ÙģتÙĩ
    0.07
    Activations Density 0.010%

    No Known Activations