© 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. 13372
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash

    This neuron detects Maven POM XML elements related to dependencies (e.g. the `<dependencies>`, `<dependency>`, `<groupId>`, `<artifactId>`, and `<version>` tags).

    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
    ());//
    -0.07
    Integration
    -0.07
    زو
    -0.07
     Vert
    -0.07
    ["
    -0.07
    ermint
    -0.06
    _MARGIN
    -0.06
    MBED
    -0.06
    Eta
    -0.06
     Floors
    -0.06
    POSITIVE LOGITS
    $conn
    0.07
     Δη
    0.06
    оруж
    0.06
     initialised
    0.06
     conscient
    0.06
     arrange
    0.06
    _tasks
    0.06
     Hector
    0.06
    _operation
    0.06
     чис
    0.05
    Activations Density 0.009%

    No Known Activations