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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38447
    Prev
    Next
    INDEX
    Explanations

    selector

    np_max-act · gemini-2.0-flash

    This neuron fires on YAML configuration keys and values typical of Kubernetes manifests (e.g. “selector,” “matchLabels,” “labels,” “spec,” “template,” “containers,” etc.).

    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
    مان
    -0.07
    鬼
    -0.07
    mouseover
    -0.07
    �
    -0.07
    (Clone
    -0.06
    JoinColumn
    -0.06
    npm
    -0.06
    ([{
    -0.06
    senha
    -0.06
    Bars
    -0.06
    POSITIVE LOGITS
     phy
    0.07
    mür
    0.07
    ought
    0.07
    orizontal
    0.07
    .Ag
    0.06
    ::↵
    0.06
     sy
    0.06
     preempt
    0.06
    gment
    0.06
     Vertical
    0.06
    Activations Density 0.001%

    No Known Activations