© 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. 71472
    Prev
    Next
    INDEX
    Explanations

    references to legal or philosophical concepts and discussions

    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
    @qq
    -0.06
    asury
    -0.06
     Yıl
    -0.06
    обов
    -0.06
    merc
    -0.06
     dumping
    -0.05
    len
    -0.05
    prites
    -0.05
    asar
    -0.05
    ĮĢ
    -0.05
    POSITIVE LOGITS
     STOCK
    0.08
     delivery
    0.08
     order
    0.08
     stocks
    0.08
     stock
    0.08
     orders
    0.07
    Dispatch
    0.07
     Delivery
    0.07
    elib
    0.07
     deliveries
    0.07
    Activations Density 0.006%

    No Known Activations