© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54037
    Prev
    Next
    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash

    The neuron is triggered by snippets of CSS code—especially tokens naming CSS properties, values, units, and regex-style patterns—i.e. it recognizes CSS syntax elements.

    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
    []):
    -0.07
    iesen
    -0.07
    安
    -0.06
    Integration
    -0.06
    ZF
    -0.06
    artner
    -0.06
     beh
    -0.06
     研
    -0.06
    imde
    -0.06
     вс
    -0.06
    POSITIVE LOGITS
    -Col
    0.07
     pollut
    0.07
    ุทร
    0.06
    .getById
    0.06
     CMD
    0.06
     вір
    0.06
    ости
    0.06
     Kuwait
    0.06
    UDGE
    0.06
     jar
    0.06
    Activations Density 0.023%

    No Known Activations