© 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. 44156
    Prev
    Next
    INDEX
    Explanations

    iae

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the Latin legal phrase “amicus curiae” (friend-of-the-court).

    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
    (Book
    -0.06
     Shotgun
    -0.06
     accusing
    -0.06
     supp
    -0.06
     tennis
    -0.06
    发现
    -0.06
     Marcos
    -0.06
    inidad
    -0.06
     پیشنه
    -0.06
     Tibetan
    -0.06
    POSITIVE LOGITS
     gums
    0.07
    分钟
    0.07
    0.06
     frost
    0.06
    DialogTitle
    0.06
     whale
    0.06
     marathon
    0.06
     перева
    0.06
    .setStyleSheet
    0.06
     три
    0.06
    Activations Density 0.001%

    No Known Activations