© 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. 125071
    Prev
    Next
    INDEX
    Explanations

    xml

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on the literal token “xml,” effectively detecting references to XML declarations or elements.

    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
     آهنگ
    -0.06
     Logical
    -0.06
     Mohamed
    -0.06
    �
    -0.06
     Tibetan
    -0.06
    -T
    -0.06
     Taiwan
    -0.06
     correlates
    -0.06
     stringByAppending
    -0.06
    ?>
    ↵
    ↵
    -0.06
    POSITIVE LOGITS
     bij
    0.07
    dej
    0.06
        	
    ↵
    0.06
    .Transparent
    0.06
     edip
    0.06
    (TABLE
    0.06
    groundColor
    0.06
    ью
    0.06
    ikip
    0.06
    .Block
    0.06
    Activations Density 0.001%

    No Known Activations