© 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. 37919
    Prev
    Next
    INDEX
    Explanations

    DUI

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of DUI or driving‐under‐the‐influence offence terminology.

    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
     therm
    -0.07
     thermostat
    -0.06
     cheesy
    -0.06
     HV
    -0.06
     Европ
    -0.06
     lb
    -0.06
     kalk
    -0.05
     konumu
    -0.05
    .testng
    -0.05
    柏
    -0.05
    POSITIVE LOGITS
     ori
    0.07
     pís
    0.07
    athering
    0.07
    dez
    0.06
     advances
    0.06
     suspects
    0.06
    aret
    0.06
    ATHER
    0.06
     influence
    0.06
     Declarations
    0.06
    Activations Density 0.004%

    No Known Activations