© 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
    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. 9267
    Prev
    Next
    INDEX
    Explanations

    previous

    np_max-act · gemini-2.0-flash

    This neuron detects numeric and dimensional tokens (e.g., numbers, “2D,” “3D,” numeric measurements) in scientific or technical text.

    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
    javascript
    -0.06
    485
    -0.06
     threaded
    -0.06
     driving
    -0.06
    ."[
    -0.06
     perfor
    -0.06
    jav
    -0.06
    FG
    -0.06
    -front
    -0.06
    ='',
    -0.06
    POSITIVE LOGITS
     údajů
    0.07
     findViewById
    0.07
     phoneNumber
    0.07
    valor
    0.07
    (ViewGroup
    0.07
     Profit
    0.07
    Describe
    0.07
    StackSize
    0.06
    itest
    0.06
    _supported
    0.06
    Activations Density 0.219%

    No Known Activations