© 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. 125255
    Prev
    Next
    INDEX
    Explanations

    onCreate

    np_max-act · gemini-2.0-flash

    The neuron fires on Android lifecycle callback method declarations—especially “onCreate” (and related overrides like onViewCreated/onAttach).

    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
    Signals
    -0.07
     Brid
    -0.07
     Sp
    -0.07
    unsigned
    -0.07
     BAR
    -0.07
    duck
    -0.06
    خیص
    -0.06
    вич
    -0.06
     서비스
    -0.06
     weiber
    -0.06
    POSITIVE LOGITS
     onCreate
    0.11
     conceived
    0.07
    .setView
    0.07
     Morm
    0.06
     TC
    0.06
     onResume
    0.06
    ystatechange
    0.06
    -days
    0.06
     Kirk
    0.06
     onUpdate
    0.06
    Activations Density 0.001%

    No Known Activations