© 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. 91320
    Prev
    Next
    INDEX
    Explanations

    ;charset

    np_max-act · gemini-2.0-flash

    The neuron activates on HTML’s `<meta>` charset declaration (e.g. “charset=UTF-8”), i.e. the character‐encoding specification in the document head.

    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
    /todo
    -0.06
    .setup
    -0.06
     infection
    -0.06
    Jordan
    -0.06
    ordion
    -0.06
    .Art
    -0.06
    欲
    -0.06
     Tracy
    -0.06
    ody
    -0.06
     подход
    -0.06
    POSITIVE LOGITS
    ;charset
    0.08
     dh
    0.07
     nn
    0.07
     corresponding
    0.06
     analogous
    0.06
     independently
    0.06
     万
    0.06
    *****
    0.06
    _DIG
    0.06
     remin
    0.06
    Activations Density 0.001%

    No Known Activations