© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65415
    Prev
    Next
    INDEX
    Explanations

    Sharia

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to mentions of Islamic legal terminology—especially “Sharia” and related law/jurisprudence terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to Islamic law and its implications in various contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()(
    -0.07
     vliv
    -0.06
    (key
    -0.06
     Fakült
    -0.06
    وو
    -0.06
    ÜM
    -0.06
    σσότε
    -0.06
    .Executor
    -0.06
    (surface
    -0.06
    Tasks
    -0.06
    POSITIVE LOGITS
    stvo
    0.06
    γου
    0.06
     needs
    0.06
    sticks
    0.06
    registered
    0.06
    windows
    0.06
    -toast
    0.06
     accommodating
    0.06
     domain
    0.06
     richness
    0.06
    Activations Density 0.009%

    No Known Activations