© 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. 127179
    Prev
    Next
    INDEX
    Explanations

    defined

    np_max-act · gemini-2.0-flash

    This neuron detects the standard PHP file‐start security guard (the “defined('_JEXEC') or die;” check) at the top of Joomla PHP source files.

    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
    LOG
    -0.07
     Migration
    -0.06
    ?>↵
    -0.06
     deterioration
    -0.06
    گران
    -0.06
     deviation
    -0.06
     SY
    -0.06
     Gry
    -0.06
    	h
    -0.06
     grapes
    -0.06
    POSITIVE LOGITS
    .down
    0.06
    جة
    0.06
    REFERRED
    0.06
     compute
    0.06
     floppy
    0.06
    ieee
    0.06
    /comments
    0.06
     #'
    0.06
     reclaimed
    0.06
    (problem
    0.06
    Activations Density 0.001%

    No Known Activations