© 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
    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. 91380
    Prev
    Next
    INDEX
    Explanations

    bragging

    np_max-act · gemini-2.0-flash

    The neuron detects boastful or self-aggrandizing language (words expressing bragging or pride).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    language expressing boasting or bragging (words/phrases indicating someone bragging).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    statements expressing boasting or prideful self-congratulation about one’s actions or achievements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    authors
    -0.06
    .path
    -0.06
     futuro
    -0.06
     kişisel
    -0.06
     competing
    -0.06
     bottled
    -0.06
     Από
    -0.06
    params
    -0.06
     hypers
    -0.06
     ayrı
    -0.06
    POSITIVE LOGITS
     Vanguard
    0.07
     Kare
    0.07
    alyze
    0.07
    FixedSize
    0.06
    바이
    0.06
    Senator
    0.06
    avy
    0.06
    分析
    0.06
    .Report
    0.06
     podařilo
    0.06
    Activations Density 0.179%

    No Known Activations