© 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. 110236
    Prev
    Next
    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens naming PCB‐footprint layer definitions (e.g. layer names like “layer”, “F.Cu”, “F.SilkS”).

    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
    	cuda
    -0.07
     CPP
    -0.07
    ContextMenu
    -0.07
    iomanip
    -0.07
     dma
    -0.07
     الأخرى
    -0.07
     가까
    -0.07
    .btnClose
    -0.06
    .DataBindings
    -0.06
    ено
    -0.06
    POSITIVE LOGITS
    storage
    0.07
    -----
    0.06
    exterity
    0.06
    Carol
    0.06
    format
    0.06
    'r
    0.06
    -grade
    0.06
     stalking
    0.06
    hunter
    0.06
    cents
    0.06
    Activations Density 0.002%

    No Known Activations