© 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. 109083
    Prev
    Next
    INDEX
    Explanations

    Latter

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the formal name or shorthand of the LDS Church (e.g. “Church of Jesus Christ of Latter-day Saints,” “LDS Church”).

    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
    ycin
    -0.07
     luật
    -0.06
     verte
    -0.06
    (Service
    -0.06
    nutrition
    -0.06
     puberty
    -0.06
     Naz
    -0.06
    _instance
    -0.06
     namely
    -0.06
    ScrollBar
    -0.06
    POSITIVE LOGITS
     Mormon
    0.08
     LDS
    0.07
     encrypted
    0.07
     EDIT
    0.07
     이동
    0.06
     Mormons
    0.06
    ักษณ
    0.06
    emics
    0.06
    PING
    0.06
    heets
    0.06
    Activations Density 0.002%

    No Known Activations