© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 43279
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    This neuron is triggered by third-person possessive pronouns (e.g. “his,” “her”).

    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
     Major
    -0.06
     Management
    -0.06
    てる
    -0.06
     Japon
    -0.06
    619
    -0.06
     spécial
    -0.06
     Every
    -0.06
     sper
    -0.06
    //#
    -0.05
     >>=
    -0.05
    POSITIVE LOGITS
     scandals
    0.07
     genders
    0.07
    REDIENT
    0.07
     manifestations
    0.07
     Janeiro
    0.06
     Like
    0.06
     рух
    0.06
     "','"
    0.06
    責
    0.06
    urchases
    0.06
    Activations Density 0.055%

    No Known Activations