© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62339
    Prev
    Next
    INDEX
    Explanations

    references to Islamic law and its foundational sources

    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
    ieren
    -0.07
     tÃŃch
    -0.07
    lish
    -0.06
     Classic
    -0.06
    022
    -0.06
    reatment
    -0.06
    elan
    -0.06
    lich
    -0.06
    ichel
    -0.06
    ıklı
    -0.06
    POSITIVE LOGITS
     Guid
    0.07
    author
    0.06
     outr
    0.06
    çĵľ
    0.06
    opoly
    0.06
     branching
    0.06
     Codec
    0.06
     peripheral
    0.06
    ظÙĩ
    0.06
     wing
    0.06
    Activations Density 0.018%

    No Known Activations