© 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. 44529
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash

    This neuron detects legal case‐citation lines (the volume–reporter–page formatting, including docket numbers and associated spacing).

    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
     estimate
    -0.07
    ランド
    -0.07
     obliged
    -0.06
    pagen
    -0.06
    cant
    -0.06
    �
    -0.06
    .Convert
    -0.06
    농
    -0.06
    посеред
    -0.06
     sto
    -0.06
    POSITIVE LOGITS
     bal
    0.06
     توص
    0.06
    <A
    0.06
    UIKit
    0.06
     PARA
    0.06
     березня
    0.06
     wool
    0.06
    .Entity
    0.06
    ↵    ↵    ↵
    0.06
    .Clone
    0.06
    Activations Density 0.002%

    No Known Activations