© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    references to religious or superstitious practices that contradict Islamic teachings

    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
    naz
    -0.08
    ANDLE
    -0.08
    ting
    -0.07
    ifdef
    -0.07
    ÑĦоÑĢми
    -0.07
    igue
    -0.07
    imbus
    -0.07
    zig
    -0.07
    ipi
    -0.07
    zÃŃ
    -0.07
    POSITIVE LOGITS
    fs
    0.07
    'icon
    0.07
    l
    0.06
    outers
    0.06
    ards
    0.06
    .uk
    0.06
    ave
    0.06
    woord
    0.06
    ships
    0.06
    fills
    0.06
    Activations Density 0.069%

    No Known Activations