Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109556
    Prev
    Next
    INDEX
    Explanations

    Web development/accessing websites

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of fetching or parsing data from a website or URL (e.g., “get the data,” “website,” “xml,” “http,” “url”).

    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
     harga
    -0.07
    classNames
    -0.06
    	elif
    -0.06
    國
    -0.06
    arin
    -0.06
    CK
    -0.06
     Locator
    -0.06
    scope
    -0.06
    Target
    -0.06
    Away
    -0.06
    POSITIVE LOGITS
    $sub
    0.07
     подк
    0.07
     Spreadsheet
    0.06
     accr
    0.06
    .Real
    0.06
    locking
    0.06
    ν
    0.06
    isl
    0.06
     cheerful
    0.06
     індив
    0.06
    Activations Density 0.043%

    No Known Activations