© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44248
    Prev
    Next
    INDEX
    Explanations

    globalization and culture

    np_max-act · gemini-2.0-flash

    programming concepts related to data formatting and parsing issues, particularly with numeric and decimal values.

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

    The neuron activates on terms related to localization settings—mentions of culture, locale, or CultureInfo in code samples.

    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
    ungeon
    -0.07
     млн
    -0.07
     missiles
    -0.06
    ustos
    -0.06
     succinct
    -0.06
     dungeons
    -0.06
    LObject
    -0.06
    .toBe
    -0.06
     eksik
    -0.06
     setBackgroundColor
    -0.06
    POSITIVE LOGITS
    すぎ
    0.07
    _CHAR
    0.06
     regex
    0.06
    _region
    0.06
     porcelain
    0.06
     Mayweather
    0.06
     Pods
    0.06
     resolved
    0.06
     attacking
    0.06
     independent
    0.06
    Activations Density 0.008%

    No Known Activations