© 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. 108845
    Prev
    Next
    INDEX
    Explanations

    APK

    np_max-act · gemini-2.0-flash

    The neuron spikes whenever the text refers to APK files and their installation or execution (e.g. commands to install/run APKs on devices or a PC).

    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
     therapy
    -0.08
     trees
    -0.07
     tree
    -0.07
     Manager
    -0.07
    руг
    -0.07
     objectType
    -0.07
    ่าส
    -0.07
     blind
    -0.06
    zet
    -0.06
    uiltin
    -0.06
    POSITIVE LOGITS
    Premium
    0.07
     apk
    0.07
     ✓
    0.06
     producción
    0.06
    approximately
    0.06
    ipur
    0.06
    _Image
    0.06
    premium
    0.06
    indy
    0.06
    ыџN
    0.06
    Activations Density 0.005%

    No Known Activations