© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30936
    Prev
    Next
    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash

    The neuron detects references to prayer and broader religious or spiritual language (e.g., mentions of God, faith, blessings, divine intervention, scripture, etc.).

    oai_token-act-pair · o4-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
    ้ส
    -0.06
    ับ
    -0.06
     steak
    -0.06
     threats
    -0.06
     reject
    -0.06
    絡
    -0.06
    ्यत
    -0.06
    оци
    -0.06
    %，
    -0.06
    werp
    -0.06
    POSITIVE LOGITS
     Pirates
    0.07
    Choosing
    0.07
    emple
    0.07
     Filipino
    0.07
    	Message
    0.07
     XCTAssert
    0.07
    [column
    0.07
     FX
    0.06
     became
    0.06
    istrator
    0.06
    Activations Density 0.003%

    No Known Activations