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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 84734
    Prev
    Next
    INDEX
    Explanations

    store

    np_max-act · gemini-2.0-flash

    The neuron activates on Core Data API class names and identifiers (e.g. NSPersistentStoreCoordinator, NSFetchedResultsController).

    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
    결
    -0.07
    -flash
    -0.07
    Wake
    -0.07
    �
    -0.07
    메
    -0.06
     puck
    -0.06
     mê
    -0.06
    .randrange
    -0.06
     parlament
    -0.06
    ым
    -0.06
    POSITIVE LOGITS
     autop
    0.06
     año
    0.06
    approved
    0.06
    toInt
    0.06
     Moved
    0.06
    ategor
    0.06
    ılıç
    0.06
    ographs
    0.06
    Unable
    0.06
    /default
    0.06
    Activations Density 0.002%

    No Known Activations