© 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 EvalsExportsinterp-engineNEWAPI 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. 58306
    Prev
    Next
    INDEX
    Explanations

    arab countries

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of place names—proper nouns referring to countries or major cities.

    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
     tho
    -0.06
    -finals
    -0.06
    (Edit
    -0.06
    ٤
    -0.06
     Anim
    -0.06
     平
    -0.06
    (alert
    -0.06
     compliant
    -0.06
    @student
    -0.05
    /cli
    -0.05
    POSITIVE LOGITS
     Morocco
    0.10
     Moroccan
    0.09
     Jordan
    0.08
              
↵
    0.08
     ammon
    0.07
    ordon
    0.07
      ↵    ↵
    0.07
     Strauss
    0.07
    ++++++++++++++++
    0.07
    ordan
    0.07
    Activations Density 0.004%

    No Known Activations