© 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. 89483
    Prev
    Next
    INDEX
    Explanations

    Adding or removing fields

    np_max-act · gemini-2.0-flash

    This neuron activates on code fragments—especially identifiers, function names, and variable names—in JavaScript/HTML relating to dynamically creating or manipulating form fields.

    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
     corpses
    -0.07
     ways
    -0.07
    .expect
    -0.07
    .Import
    -0.07
    4
    -0.07
     printers
    -0.06
    ывал
    -0.06
    viz
    -0.06
     excitement
    -0.06
    Still
    -0.06
    POSITIVE LOGITS
     kø
    0.06
    StartupScript
    0.06
    orges
    0.06
    ?>
    0.06
     Eb
    0.06
    οντας
    0.06
     Hazard
    0.06
     Zot
    0.06
    	tab
    0.06
    !!}</
    0.06
    Activations Density 0.028%

    No Known Activations