© 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
    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. 7786
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron detects the main content nouns in “X and Y” coordination phrases.

    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
    ฤษ
    -0.08
    ','','
    -0.06
     škol
    -0.06
     qed
    -0.06
    Left
    -0.06
    طور
    -0.06
    ريف
    -0.06
    -haired
    -0.06
     поход
    -0.06
     znám
    -0.06
    POSITIVE LOGITS
     Country
    0.08
    gio
    0.07
     영화
    0.07
    _weather
    0.07
     câ
    0.07
    字符串
    0.07
    Country
    0.07
    .Redis
    0.07
    <Float
    0.07
     MyBase
    0.07
    Activations Density 0.076%

    No Known Activations