© 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. 128435
    Prev
    Next
    INDEX
    Explanations

    -repeat

    np_max-act · gemini-2.0-flash

    The neuron fires on AngularJS directive attributes (tokens beginning with “ng-” such as ng-init, ng-if, ng-repeat, ng-click, 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
    /command
    -0.07
    -answer
    -0.06
    .xaxis
    -0.06
     دهد
    -0.06
    produce
    -0.06
     rencont
    -0.06
    [count
    -0.06
    _RECT
    -0.06
     locator
    -0.06
    통신
    -0.06
    POSITIVE LOGITS
    precio
    0.07
    огра
    0.07
    _thumbnail
    0.07
     G
    0.06
     networking
    0.06
     Continued
    0.06
     Regardless
    0.06
    umption
    0.06
     Performing
    0.06
    하였다
    0.06
    Activations Density 0.003%

    No Known Activations