© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91408
    Prev
    Next
    INDEX
    Explanations

    XML code

    np_max-act · gemini-2.0-flash

    The neuron fires on XML/HTML structural tokens—specifically opening‐tag markers (“<”), tag names (e.g. component, option, entry), and attribute names/assignment syntax inside angle brackets.

    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
    ÜM
    -0.07
    ため
    -0.06
    .requestFocus
    -0.06
    該
    -0.06
    usch
    -0.06
     EGL
    -0.06
    Au
    -0.06
    �
    -0.06
     등
    -0.06
     conservative
    -0.06
    POSITIVE LOGITS
    _hosts
    0.07
     experienced
    0.07
     Terror
    0.07
     flea
    0.07
    putc
    0.07
     milit
    0.06
    éc
    0.06
     Occupational
    0.06
    lk
    0.06
     Media
    0.06
    Activations Density 0.005%

    No Known Activations