© 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. 7643
    Prev
    Next
    INDEX
    Explanations

    Childbirth/death

    np_max-act · gemini-2.0-flash

    The neuron is detecting references to pregnancy loss or infant death.

    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
    Skills
    -0.06
    Eval
    -0.06
     dataSource
    -0.06
     вд
    -0.06
    groups
    -0.06
     "("
    -0.06
    UserProfile
    -0.06
    év
    -0.06
    onclick
    -0.06
    .groupby
    -0.06
    POSITIVE LOGITS
     restraint
    0.07
     after
    0.07
    perial
    0.07
     прок
    0.07
     ':'
    0.07
     Imperial
    0.06
    quisar
    0.06
     Italians
    0.06
     inherited
    0.06
    功能
    0.06
    Activations Density 0.012%

    No Known Activations