© 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. 30000
    Prev
    Next
    INDEX
    Explanations

    XML

    np_max-act · gemini-2.0-flash

    The neuron fires on XML-related markup and vocabulary (e.g. “xml,” file tags, prolog declarations, and angle-bracketed 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
    containers
    -0.06
    	onClick
    -0.06
    xmax
    -0.06
    roit
    -0.06
     د
    -0.06
     menn
    -0.06
    ecurity
    -0.06
    .scss
    -0.06
    Cách
    -0.06
    Sou
    -0.06
    POSITIVE LOGITS
     dwelling
    0.08
    (nb
    0.08
     Dip
    0.07
    $q
    0.06
    adio
    0.06
     gritty
    0.06
     residence
    0.06
     Released
    0.06
    -pad
    0.06
    uges
    0.06
    Activations Density 0.031%

    No Known Activations