© 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. 90749
    Prev
    Next
    INDEX
    Explanations

    Family relations

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting biographical details about lineage and succession—mentions of family relationships (e.g. son, mother, father), birthdates, reign years, and other dynasty-related facts.

    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
     aud
    -0.07
     graphite
    -0.07
    (base
    -0.06
    (player
    -0.06
    -indent
    -0.06
     الض
    -0.06
     dough
    -0.06
    lectric
    -0.06
     declining
    -0.06
    (property
    -0.06
    POSITIVE LOGITS
    _again
    0.07
     своїх
    0.07
    ONGODB
    0.06
     kommun
    0.06
     공고
    0.06
    _last
    0.06
     notre
    0.06
     pharmacist
    0.06
    argar
    0.06
    완
    0.06
    Activations Density 0.024%

    No Known Activations