© 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. 91378
    Prev
    Next
    INDEX
    Explanations

    sports teams and companies

    np_max-act · gemini-2.0-flash

    This neuron activates on words referring to collective groups or organizations (e.g. “men,” “team,” “company,” “boys”).

    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
     notable
    -0.07
     tahmin
    -0.07
    etik
    -0.06
     Palin
    -0.06
     Rings
    -0.06
     exacerbated
    -0.06
     pixels
    -0.06
    Scalars
    -0.06
    urdy
    -0.06
     万元
    -0.06
    POSITIVE LOGITS
    .props
    0.07
     پرس
    0.07
     spolu
    0.07
    \Migrations
    0.06
     ActionTypes
    0.06
    )const
    0.06
    /operators
    0.06
    ')->__('
    0.06
     Propel
    0.06
     Rohingya
    0.06
    Activations Density 0.043%

    No Known Activations