© 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. 109755
    Prev
    Next
    INDEX
    Explanations

    xml

    np_max-act · gemini-2.0-flash

    The neuron fires on the “xml” token in XML prolog declarations (e.g. the "<?xml version=…?>" header).

    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
    _per
    -0.07
    Сп
    -0.06
    าจ
    -0.06
     Gar
    -0.06
     ح
    -0.06
    inston
    -0.06
    झ
    -0.06
    れて
    -0.06
    คโน
    -0.06
    .Ref
    -0.06
    POSITIVE LOGITS
    (KeyCode
    0.07
    >Error
    0.07
    (Color
    0.06
    (robot
    0.06
     crimes
    0.06
    :add
    0.06
     Reliable
    0.06
    (withIdentifier
    0.06
     Guidelines
    0.06
    <table
    0.06
    Activations Density 0.001%

    No Known Activations