© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73826
    Prev
    Next
    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash

    The neuron activates on the start of HTML/XML closing tags (i.e. the “</” token) throughout the document.

    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
     plus
    -0.07
    uyệt
    -0.07
    Im
    -0.07
    чи
    -0.07
    ازی
    -0.07
    .sim
    -0.07
    irim
    -0.07
     interactions
    -0.07
     Wifi
    -0.06
     compounds
    -0.06
    POSITIVE LOGITS
    	
    ↵
    ↵
    0.08
    (Encoding
    0.07
    ("</
    0.07
     @"↵
    0.07
    dbh
    0.06
     bulun
    0.06
    </
    0.06
     παρ
    0.06
    翻
    0.06
     Βασ
    0.06
    Activations Density 0.010%

    No Known Activations