© 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. 80188
    Prev
    Next
    INDEX
    Explanations

    customers

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect commerce-related transaction terms (e.g. order, purchase, discount).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    expressions of gratitude and satisfaction with customer service.

    oai_token-act-pair · gpt-4o-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
    �
    -0.07
    _HEADERS
    -0.07
    Organization
    -0.06
    三级
    -0.06
    _CAT
    -0.06
    /temp
    -0.06
    dü
    -0.06
    .respond
    -0.06
     unofficial
    -0.06
     Charity
    -0.06
    POSITIVE LOGITS
     consequential
    0.07
     возв
    0.06
     illuminate
    0.06
    nullptr
    0.06
     discontinued
    0.06
     تقو
    0.06
     overlook
    0.06
    ilarity
    0.06
     SPI
    0.06
    flate
    0.06
    Activations Density 0.098%

    No Known Activations