© 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. 128227
    Prev
    Next
    INDEX
    Explanations

    reincarnation

    np_max-act · gemini-2.0-flash

    This neuron is specialized to spot the word “reincarnate” or “reincarnation” (via its subword pieces).

    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
     remembers
    -0.07
     Roberto
    -0.06
     spectro
    -0.06
    �습니다
    -0.06
    inou
    -0.06
     QCOMPARE
    -0.06
    _equal
    -0.06
    .dp
    -0.06
    lerden
    -0.06
     λέ
    -0.06
    POSITIVE LOGITS
    .Files
    0.07
    .OrdinalIgnoreCase
    0.06
    alsex
    0.06
    athi
    0.06
    วาม
    0.06
    +='
    0.06
     Ivory
    0.06
    TZ
    0.06
    .syntax
    0.06
     ASN
    0.06
    Activations Density 0.015%

    No Known Activations