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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109227
    Prev
    Next
    INDEX
    Explanations

    Amazon product IDs

    np_max-act · gemini-2.0-flash

    This neuron activates on product identifier codes (alphanumeric model or SKU strings like “B078GWRC1J” or “B089X86H73”)

    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
     Caucas
    -0.07
    арат
    -0.07
     Hercules
    -0.07
     //[
    -0.07
    _ATTACK
    -0.07
     Cut
    -0.07
    _requested
    -0.06
     disemb
    -0.06
     Jing
    -0.06
    änge
    -0.06
    POSITIVE LOGITS
     guarantees
    0.06
    (SP
    0.06
     concentrating
    0.06
     Practical
    0.06
     trú
    0.06
    ữ
    0.06
    }/#{
    0.05
    Incomplete
    0.05
     gece
    0.05
    něné
    0.05
    Activations Density 0.008%

    No Known Activations