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. 130428
    Prev
    Next
    INDEX
    Explanations

    offers and promotions

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects marketing‐offer terms—words referring to special promotions, discounts, and similar sales incentives.

    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
    weight
    -0.06
     THREAD
    -0.06
    .rmtree
    -0.06
     이런
    -0.06
    आप
    -0.06
     Λ
    -0.06
     kraje
    -0.06
    zet
    -0.06
     necessário
    -0.06
     soma
    -0.06
    POSITIVE LOGITS
    вищ
    0.07
    ạy
    0.07
    :UI
    0.07
    314
    0.06
    ľ
    0.06
     UPDATED
    0.06
    voy
    0.06
    lush
    0.06
     Provincial
    0.06
     captions
    0.06
    Activations Density 0.014%

    No Known Activations