© 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. 41052
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the first‐person pronoun “I.”

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

    The neuron detects the first-person pronoun "I", especially when used in user questions asking about the speaker.

    oai_token-act-pair · gpt-5-miniTriggered 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
    Deploy
    -0.07
     ห
    -0.07
     değerlendir
    -0.06
     Charity
    -0.06
     assembler
    -0.06
     عن
    -0.06
    .codes
    -0.06
    WithName
    -0.06
     правила
    -0.06
    +n
    -0.06
    POSITIVE LOGITS
     itinerary
    0.06
    99
    0.06
    ì
    0.06
    ObjectContext
    0.06
    资金
    0.06
    جة
    0.06
    (火
    0.06
     четвер
    0.06
    aggio
    0.06
     prueba
    0.06
    Activations Density 0.015%

    No Known Activations