Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 86347
    Prev
    Next
    INDEX
    Explanations

    spring

    np_max-act · gemini-2.0-flash

    The neuron fires on Maven/Gradle build snippets referring to “spring-boot” (i.e. Spring Boot dependency coordinates).

    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
     flirt
    -0.07
    ())[
    -0.07
    -haired
    -0.07
     volunt
    -0.06
     Dani
    -0.06
     stacking
    -0.06
    overview
    -0.06
    ForObject
    -0.06
     sopr
    -0.06
     présent
    -0.06
    POSITIVE LOGITS
    .minecraft
    0.07
     نقد
    0.07
     ได
    0.06
    emetery
    0.06
    -resolution
    0.06
    Toggle
    0.06
     /\.
    0.06
     Stalin
    0.06
    ('.'
    0.06
     shedding
    0.06
    Activations Density 0.001%

    No Known Activations