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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90884
    Prev
    Next
    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash

    The neuron activates on GUI layout‐related terms and parameters (e.g. “Layout,” “Data,” “fill,” attachments, weights), i.e. code constructs that configure component layouts.

    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
     HttpStatus
    -0.07
     Beste
    -0.07
     iconName
    -0.07
     меньше
    -0.07
    الیا
    -0.06
     indoors
    -0.06
    ,则
    -0.06
    favicon
    -0.06
     VALUES
    -0.06
     leží
    -0.06
    POSITIVE LOGITS
    .Priority
    0.07
     OT
    0.06
    座
    0.06
     Navbar
    0.06
     transports
    0.06
     OU
    0.06
    载
    0.06
    reement
    0.06
     Evan
    0.06
    (userid
    0.05
    Activations Density 0.007%

    No Known Activations