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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109263
    Prev
    Next
    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash

    This neuron detects references to Paul’s letter to the Romans—mentions of “the church in Rome,” the historical/cultural setting, and related contextual details.

    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
    ience
    -0.07
    utory
    -0.07
    -car
    -0.06
    ognito
    -0.06
     Cialis
    -0.06
     Beginner
    -0.06
     choir
    -0.06
    Thus
    -0.06
    /news
    -0.06
    IVED
    -0.06
    POSITIVE LOGITS
     DRIVE
    0.06
     chạy
    0.06
    .setItem
    0.06
    .TryGetValue
    0.06
     onSelect
    0.06
     bx
    0.06
     ketogenic
    0.06
    먹
    0.06
    推
    0.06
     Madame
    0.06
    Activations Density 0.049%

    No Known Activations