Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129543
    Prev
    Next
    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases related to religion or religious contexts.

    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
    coupon
    -0.06
     взгляд
    -0.06
    662
    -0.06
    आप
    -0.06
    ≤
    -0.06
    การใช
    -0.06
    建
    -0.06
    действ
    -0.06
    буд
    -0.06
    xx
    -0.06
    POSITIVE LOGITS
    країн
    0.07
     Caval
    0.07
     covered
    0.07
     unreachable
    0.06
    	Y
    0.06
    acky
    0.06
     entitled
    0.06
     bö
    0.06
    (EIF
    0.06
     ylabel
    0.06
    Activations Density 0.016%

    No Known Activations