© 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. 30536
    Prev
    Next
    INDEX
    Explanations

    Fictional narrative descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects the special placeholder tokens for character names (e.g., “NAME_1,” “NAME_2,” etc.).

    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
     rumpe
    -0.07
    connection
    -0.07
    .bunifu
    -0.07
     desper
    -0.06
     MAGIC
    -0.06
    スカ
    -0.06
     yazar
    -0.06
    Chan
    -0.06
    Cake
    -0.06
    -list
    -0.06
    POSITIVE LOGITS
    ButtonItem
    0.06
     majority
    0.06
    .Object
    0.06
     aument
    0.06
    Notification
    0.06
    (categories
    0.06
    (import
    0.06
     disability
    0.05
    appiness
    0.05
     kommen
    0.05
    Activations Density 0.038%

    No Known Activations