© 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. 29569
    Prev
    Next
    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “app” (in identifiers or tokens like “App,” “app,” “appPaths,” “appDatabase,” “app.js,” etc.).

    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
     slaughtered
    -0.08
    ONSE
    -0.08
    jug
    -0.07
     Decision
    -0.07
    oul
    -0.07
     Nielsen
    -0.07
    üre
    -0.07
    olet
    -0.07
     Trib
    -0.07
     Sağlık
    -0.07
    POSITIVE LOGITS
     app
    0.15
     App
    0.12
    App
    0.11
     apps
    0.11
     APP
    0.09
    .app
    0.09
     Apps
    0.09
    app
    0.09
    /apps
    0.09
    FF
    0.09
    Activations Density 0.035%

    No Known Activations