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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 101791
    Prev
    Next
    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash

    The neuron fires on UI layout‐management code, especially tokens like “Layout” and “Data” (e.g. GridLayout/GridData setup and margin settings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms associated with XML processing and compression.

    oai_token-act-pair · gpt-4o-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
    chooser
    -0.06
    umericUpDown
    -0.06
    _Request
    -0.06
     '((
    -0.06
    _BOOK
    -0.06
    **/↵↵
    -0.06
    あり
    -0.06
    があり
    -0.06
    .DropDown
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     resisted
    0.07
    Related
    0.07
    MD
    0.07
    Instructions
    0.06
    trainer
    0.06
    INSERT
    0.06
    ıldığında
    0.06
     Copyright
    0.06
     atm
    0.06
    instructions
    0.06
    Activations Density 0.010%

    No Known Activations