© 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. 29472
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS/Javascript code

    np_max-act · gemini-2.0-flash

    This neuron fires on JavaScript code snippets, marking tokens like `function`, DOM API calls (e.g. `document.querySelector`), and style‐setting expressions.

    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
    regexp
    -0.07
    -hole
    -0.06
    ğitim
    -0.06
    adena
    -0.06
     lesson
    -0.06
    켜
    -0.06
    �
    -0.06
     remembered
    -0.06
     علي
    -0.06
     доме
    -0.06
    POSITIVE LOGITS
    artisan
    0.07
    Wrap
    0.06
    song
    0.06
    :['
    0.06
    연
    0.06
     výro
    0.06
     setContentView
    0.06
     Amerikan
    0.06
    prix
    0.06
     плю
    0.06
    Activations Density 0.031%

    No Known Activations