© 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. 37992
    Prev
    Next
    INDEX
    Explanations

    bombs and explosions

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of nuclear‐weapon terminology (e.g. “bomb,” “nuclear,” “weapon,” “explosion”).

    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
    .advance
    -0.07
     excitement
    -0.07
     Cafe
    -0.07
     Aging
    -0.07
     Bread
    -0.07
     
    -0.06
    .logout
    -0.06
    \Bridge
    -0.06
    Generation
    -0.06
    -е
    -0.06
    POSITIVE LOGITS
     HEAP
    0.06
    名字
    0.06
     (/
    0.06
     presumed
    0.06
     ampl
    0.06
     MG
    0.06
    ymmetric
    0.06
    ceu
    0.06
    'acc
    0.06
     Strauss
    0.06
    Activations Density 0.005%

    No Known Activations