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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12162
    Prev
    Next
    INDEX
    Explanations

    alphanumeric combinations

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming the reading‐list categories (like “fiction,” “nonfiction,” “science,” and “books”).

    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
    ービス
    -0.06
     Wikipedia
    -0.06
    ersive
    -0.06
    (chat
    -0.06
    (calendar
    -0.06
     coch
    -0.06
    yg
    -0.06
     minced
    -0.06
    -random
    -0.06
    jin
    -0.06
    POSITIVE LOGITS
    -found
    0.06
    EmailAddress
    0.06
     얼마
    0.06
    (Id
    0.06
    oui
    0.06
     Definitions
    0.06
     exped
    0.06
    andro
    0.06
     hopeful
    0.06
     \"
    0.06
    Activations Density 0.223%

    No Known Activations