© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126660
    Prev
    Next
    INDEX
    Explanations

    Churches and religious art

    np_max-act · gemini-2.0-flash

    This neuron activates on words naming Christian feasts or church dedications (e.g. “Ascension,” “Transfiguration,” “Visitation,” “Assumption,” 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
    OGLE
    -0.06
    prav
    -0.06
     Antarctica
    -0.06
    izyon
    -0.06
    δά
    -0.06
    .leadingAnchor
    -0.06
    른
    -0.06
     niece
    -0.06
    ılı
    -0.06
     finding
    -0.06
    POSITIVE LOGITS
     arg
    0.08
    Ads
    0.07
     severed
    0.07
     bowling
    0.06
    .asarray
    0.06
    \Notifications
    0.06
     Listed
    0.06
     asc
    0.06
     Carb
    0.06
    (statearr
    0.06
    Activations Density 0.008%

    No Known Activations