© 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. 110626
    Prev
    Next
    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash

    This neuron fires on the subword “ing,” most prominently when it appears in the word “boxing,” so it essentially detects mentions of the sport “boxing.”

    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
     فروش
    -0.07
     message
    -0.07
     mData
    -0.06
     firmware
    -0.06
     sw
    -0.06
    (T
    -0.06
    تق
    -0.06
     joy
    -0.06
    搜
    -0.06
    scrollView
    -0.06
    POSITIVE LOGITS
     boxer
    0.11
     Boxing
    0.10
     boxing
    0.10
     lex
    0.07
     đặt
    0.07
    ighted
    0.06
     Tommy
    0.06
     Brewing
    0.06
     Norman
    0.06
     space
    0.06
    Activations Density 0.008%

    No Known Activations