© 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. 44532
    Prev
    Next
    INDEX
    Explanations

    code related text

    np_max-act · gemini-2.0-flash

    This neuron highlights tokens that name or label the classification categories (e.g. the “_question” class identifiers like tax_question, chat_bot_question, other_question).

    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
    _jwt
    -0.08
     Nous
    -0.07
     Sunset
    -0.07
    -ton
    -0.07
    til
    -0.07
     clipboard
    -0.06
     Miranda
    -0.06
    bk
    -0.06
    LAB
    -0.06
     diner
    -0.06
    POSITIVE LOGITS
     approximate
    0.07
     абсолютно
    0.07
     όπου
    0.06
     التاريخ
    0.06
     follando
    0.06
     Số
    0.06
    Accessibility
    0.06
    的一
    0.06
    /"
    0.06
     그래서
    0.06
    Activations Density 0.025%

    No Known Activations