© 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. 29374
    Prev
    Next
    INDEX
    Explanations

    titles and references to books discussing public philosophy and moral questions

    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
     inset
    -0.07
    unya
    -0.06
    ouro
    -0.06
    edly
    -0.06
    kers
    -0.06
    illon
    -0.06
    emiz
    -0.06
    azon
    -0.06
    dato
    -0.06
     Recap
    -0.05
    POSITIVE LOGITS
    alink
    0.08
     Contains
    0.07
    åħ¨éĿ¢
    0.07
    resents
    0.07
    WithContext
    0.07
     This
    0.06
    <j
    0.06
    Contains
    0.06
    INCLUDE
    0.06
    978
    0.06
    Activations Density 0.015%

    No Known Activations