© 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. 29484
    Prev
    Next
    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash

    This neuron activates on the XML attribute “app:showAsAction” (specifically the tokens “show,” “As,” and “Action” and its values like “always,” “never,” or “ifRoom”) in Android menu definitions.

    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
    教师
    -0.07
    िजल
    -0.06
     навчання
    -0.06
     stake
    -0.06
     중국
    -0.06
     stirring
    -0.06
     RuntimeMethod
    -0.06
     труда
    -0.06
     проб
    -0.06
    ع
    -0.06
    POSITIVE LOGITS
     yelling
    0.06
    .Dispatcher
    0.06
     ff
    0.06
    CHECK
    0.06
    (browser
    0.06
     г
    0.06
    Op
    0.06
    .UInt
    0.06
    (use
    0.06
     incr
    0.06
    Activations Density 0.000%

    No Known Activations