© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59422
    Prev
    Next
    INDEX
    Explanations

    Lists of names

    np_max-act · gemini-2.0-flash

    names of notable individuals associated with specific fields or contributions in culture or academia.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @xinyanhu8

    This neuron identifies tokens that are parts of people’s names (especially surnames) in list entries.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    .Direct
    -0.07
     为
    -0.06
    .hex
    -0.06
    Escape
    -0.06
     Diaz
    -0.06
    ремя
    -0.06
    EST
    -0.06
    理
    -0.06
     صنایع
    -0.06
    im
    -0.06
    POSITIVE LOGITS
     mund
    0.07
     geld
    0.06
     mattered
    0.06
    戶
    0.06
     dựng
    0.06
     Mourinho
    0.06
     prag
    0.06
    ViewItem
    0.06
    ponder
    0.06
     suicides
    0.06
    Activations Density 0.028%

    No Known Activations