© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126681
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    This neuron detects inline HTML event‐handler attributes (e.g. onclick, onchange) and their JavaScript calls.

    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
    HG
    -0.06
    'class
    -0.06
    /tmp
    -0.06
    omething
    -0.06
     Minority
    -0.06
    090
    -0.06
     pantry
    -0.06
    ürn
    -0.06
     adaptable
    -0.06
    	UP
    -0.06
    POSITIVE LOGITS
    огою
    0.07
    登录
    0.06
     definitive
    0.06
     scholar
    0.06
     Fund
    0.06
    gments
    0.06
     BRO
    0.06
     şik
    0.06
     DataGridViewCellStyle
    0.06
    VAS
    0.06
    Activations Density 0.003%

    No Known Activations