© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89143
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    This neuron detects code that constructs or configures VS Code TreeItem objects (e.g. instantiating TreeItem and setting its CollapsibleState).

    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
     utilisateur
    -0.07
    ontvangst
    -0.07
    звичай
    -0.07
     य
    -0.06
    توبر
    -0.06
    ians
    -0.06
    ข
    -0.06
     katılım
    -0.06
    COD
    -0.06
     Sponge
    -0.06
    POSITIVE LOGITS
    ='',
    0.07
    	perror
    0.06
     taraf
    0.06
     Wolff
    0.06
     VF
    0.06
    قب
    0.06
     Helpful
    0.06
     České
    0.06
    公共
    0.06
    �
    0.06
    Activations Density 0.063%

    No Known Activations