© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43156
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric year expressions (e.g. “1996”, “2001”) and their surrounding punctuation (parentheses, hyphens) in the text.

    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
    .Result
    -0.06
     invaders
    -0.06
    horse
    -0.06
    (Block
    -0.06
    =sum
    -0.06
     prejudice
    -0.06
     Movies
    -0.05
     readers
    -0.05
     nutrition
    -0.05
    true
    -0.05
    POSITIVE LOGITS
     wnd
    0.07
    围
    0.07
     ¡
    0.07
    Sau
    0.07
    ordova
    0.07
    MORE
    0.06
     Spacer
    0.06
     पहच
    0.06
     mixin
    0.06
     işlemi
    0.06
    Activations Density 0.094%

    No Known Activations