© 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. 89674
    Prev
    Next
    INDEX
    Explanations

    Changes

    np_max-act · gemini-2.0-flash

    This neuron fires on the XML attribute name “configChanges” (the “Changes” token) in Android manifest entries.

    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
    Pa
    -0.07
     homogeneous
    -0.07
    lcd
    -0.07
     Verg
    -0.07
    егист
    -0.06
     stakes
    -0.06
    .keyword
    -0.06
    .go
    -0.06
    _you
    -0.06
     рам
    -0.06
    POSITIVE LOGITS
    -Javadoc
    0.08
    ратить
    0.07
    форт
    0.07
     людей
    0.06
     Країна
    0.06
     Cheers
    0.06
    OPTIONS
    0.06
     رشته
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
     belli
    0.06
    Activations Density 0.000%

    No Known Activations