© 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. 92511
    Prev
    Next
    INDEX
    Explanations

    visibility

    np_max-act · gemini-2.0-flash

    This neuron detects XML “visibility” attributes (e.g. android:visibility="…") in layout files.

    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
    _INTEGER
    -0.08
     nfs
    -0.07
    unittest
    -0.07
     Alone
    -0.06
     Edited
    -0.06
     MainForm
    -0.06
    094
    -0.06
     Letters
    -0.06
     No
    -0.06
     LoginPage
    -0.06
    POSITIVE LOGITS
    .setVisibility
    0.07
    Away
    0.07
     Vision
    0.06
    0.06
    ี้
    0.06
    ivil
    0.06
    veriş
    0.06
    　イ
    0.06
     вико
    0.06
    。これ
    0.06
    Activations Density 0.002%

    No Known Activations