© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6069
    Prev
    Next
    INDEX
    Explanations

    simple

    np_max-act · gemini-2.0-flash

    This neuron detects usages of the word “simple” (often as “is simple” or “simple:”) that introduce a rationale or explanation.

    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
    Cat
    -0.06
     особи
    -0.06
     salon
    -0.06
     Kosten
    -0.06
    ybrid
    -0.06
     Cross
    -0.06
     computed
    -0.06
    -opening
    -0.06
    META
    -0.06
    PING
    -0.06
    POSITIVE LOGITS
     بسي
    0.07
    (itr
    0.07
    breadcrumbs
    0.06
    navbarSupportedContent
    0.06
     YYS
    0.06
     esta
    0.06
     inse
    0.06
     {?>↵
    0.06
     mitochond
    0.06
     lep
    0.06
    Activations Density 0.019%

    No Known Activations