© 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. 131007
    Prev
    Next
    INDEX
    Explanations

    references to Jewish identity and related social, cultural, and historical themes

    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
     cục
    -0.07
    afs
    -0.07
    .bin
    -0.07
    ntag
    -0.07
    acher
    -0.07
    apan
    -0.07
    liž
    -0.06
    bjerg
    -0.06
    akis
    -0.06
    asury
    -0.06
    POSITIVE LOGITS
     Settlement
    0.08
     settlement
    0.08
     experiment
    0.08
     Landing
    0.07
     bu
    0.07
     settlements
    0.07
     Charter
    0.07
    æ®ĸ
    0.07
     landing
    0.07
     settling
    0.07
    Activations Density 0.055%

    No Known Activations