Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85962
    Prev
    Next
    INDEX
    Explanations

    United States

    np_max-act · gemini-2.0-flash

    instructions and guidelines related to safe practices in specific contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of the United States or American context (e.g. “US,” “United States,” “American”).

    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
     важно
    -0.07
    ides
    -0.07
     Qing
    -0.07
     Addiction
    -0.06
     المعلومات
    -0.06
    882
    -0.06
    Picker
    -0.06
    _texture
    -0.06
     Ты
    -0.06
     Scrolls
    -0.06
    POSITIVE LOGITS
    (笑
    0.07
    เรา
    0.07
     виг
    0.06
    .getContentPane
    0.06
     provoc
    0.06
     gra
    0.06
     footh
    0.06
    -{
    0.06
     وظ
    0.06
    Ngày
    0.06
    Activations Density 0.105%

    No Known Activations