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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12440
    Prev
    Next
    INDEX
    Explanations

    extend

    np_max-act · gemini-2.0-flash

    The neuron activates on inheritance-related keywords in code, primarily detecting “extends” (and related “override”) in class declarations.

    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
    ’autres
    -0.06
     ของ
    -0.06
     необхід
    -0.06
     voor
    -0.06
    (history
    -0.06
     coil
    -0.06
     Bates
    -0.06
    еним
    -0.06
    ของ
    -0.06
     смер
    -0.06
    POSITIVE LOGITS
    estado
    0.08
    Featured
    0.07
    movie
    0.07
    prene
    0.07
     Hurricane
    0.07
    IPA
    0.06
    migration
    0.06
    Favorite
    0.06
     snacks
    0.06
    _regeneration
    0.06
    Activations Density 0.007%

    No Known Activations