© 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
    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. 44747
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    This neuron responds to bits of legal citation formatting—volume numbers, reporter abbreviations (e.g. “de novo,” “S.E.2d”), and related tokens that appear in case‐law citations.

    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
     Fa
    -0.07
     albums
    -0.06
    eft
    -0.06
    ờ
    -0.06
    .house
    -0.06
     ure
    -0.06
    _table
    -0.06
    τικό
    -0.06
    	grid
    -0.06
     podařilo
    -0.06
    POSITIVE LOGITS
     ку
    0.06
    _ENCODING
    0.06
     Ans
    0.06
    中國
    0.06
    ,看
    0.06
     Attendance
    0.06
     mayores
    0.06
    奖
    0.06
     DISTRIBUT
    0.06
     exceeding
    0.06
    Activations Density 0.012%

    No Known Activations