Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84549
    Prev
    Next
    INDEX
    Explanations

    coupon

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to the token “coupon” (and its plural “coupons”), i.e. it detects mentions of coupons.

    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
    818
    -0.07
     OSX
    -0.07
    	DEBUG
    -0.07
    тою
    -0.07
     Bat
    -0.07
     cliffs
    -0.06
    Đây
    -0.06
    ircle
    -0.06
     Jing
    -0.06
     Static
    -0.06
    POSITIVE LOGITS
    Coupon
    0.09
     coupon
    0.09
     voucher
    0.09
     coupons
    0.09
     Coupon
    0.08
    coupon
    0.08
    roupon
    0.07
     çeşit
    0.07
    webElementProperties
    0.07
     vouchers
    0.07
    Activations Density 0.002%

    No Known Activations