© 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. 109142
    Prev
    Next
    INDEX
    Explanations

    commas and quotes

    np_max-act · gemini-2.0-flash

    This neuron detects JSON object property names (the keys) in REST/JSON data.

    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
    _CE
    -0.07
    さま
    -0.07
    akk
    -0.06
    ディース
    -0.06
     Piet
    -0.06
     ",");↵
    -0.06
    IPP
    -0.06
    ’app
    -0.06
     Duty
    -0.06
     ribs
    -0.06
    POSITIVE LOGITS
     estão
    0.08
    .Runtime
    0.07
    .StylePriority
    0.06
    LA
    0.06
     حالة
    0.06
     многих
    0.06
    Ln
    0.06
    (GameObject
    0.06
     ########.
    0.06
    bstract
    0.06
    Activations Density 0.033%

    No Known Activations