© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12728
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash

    phrases related to technology and online services.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to personal pronouns—especially first‐ and second‐person possessives like “my” and “your.”

    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
    articles
    -0.07
     numeric
    -0.07
     briefing
    -0.06
    -call
    -0.06
     beaches
    -0.06
    ندا
    -0.06
    odelist
    -0.06
     toddler
    -0.06
    cek
    -0.06
    undreds
    -0.06
    POSITIVE LOGITS
     your
    0.07
     Your
    0.07
    .*(
    0.07
     bị
    0.07
    ><![
    0.07
     yPos
    0.06
     brill
    0.06
     keras
    0.06
    +W
    0.06
     příprav
    0.06
    Activations Density 0.061%

    No Known Activations