© 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. 89429
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects numeric values (integers, decimals, and fractions) in the 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
    handling
    -0.07
     needy
    -0.06
    rnd
    -0.06
    				       
    -0.05
    orde
    -0.05
     вищ
    -0.05
    $PostalCodesNL
    -0.05
    operation
    -0.05
    79
    -0.05
    urved
    -0.05
    POSITIVE LOGITS
     터
    0.07
    <Input
    0.07
     چنان
    0.07
     chống
    0.07
    edeyse
    0.07
     obyvatel
    0.07
     warp
    0.07
     może
    0.07
     manifesto
    0.06
    ‌ترین
    0.06
    Activations Density 0.002%

    No Known Activations