© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128800
    Prev
    Next
    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash

    The neuron fires on Java standard‐library package and class names (e.g. “java”, “javax”, “java.nio”, etc.).

    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
     Rahul
    -0.06
    .='<
    -0.06
    ±ظ
    -0.06
     flexGrow
    -0.06
    ่น
    -0.06
    DrawerToggle
    -0.06
    	RTLR
    -0.06
    閉
    -0.06
     اصفه
    -0.06
    _CLK
    -0.06
    POSITIVE LOGITS
     java
    0.11
    java
    0.08
     králov
    0.07
    atoes
    0.07
    Schedule
    0.07
    REMOTE
    0.07
     blades
    0.07
    chedules
    0.07
     have
    0.07
    Locale
    0.07
    Activations Density 0.004%

    No Known Activations