© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126884
    Prev
    Next
    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    The neuron fires on subword tokens that occur in quoted etymological or technical‐term excerpts (e.g. the Greek roots and other word‐origin fragments shown inside quotation marks).

    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
    .tbl
    -0.07
    ovaného
    -0.07
    oň
    -0.07
    goto
    -0.06
    たら
    -0.06
     bathrooms
    -0.06
    ЕР
    -0.06
    patrick
    -0.06
    ал
    -0.06
     fuzz
    -0.05
    POSITIVE LOGITS
    :bold
    0.07
     OutlineInputBorder
    0.07
     розви
    0.07
    instead
    0.06
     Bilg
    0.06
     chân
    0.06
    imizin
    0.06
    Actualizar
    0.06
     रहत
    0.06
     sexuales
    0.06
    Activations Density 0.015%

    No Known Activations