© 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. 12522
    Prev
    Next
    INDEX
    Explanations

    Cause

    np_max-act · gemini-2.0-flash

    This neuron responds to Portuguese-language legal petition text, in particular boilerplate phrasing around real‐estate enforcement (e.g. referring to “imóvel,” “situado em …,” contracts and civil‐code articles).

    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
     чаще
    -0.07
    idi
    -0.07
    logged
    -0.07
    anki
    -0.06
     Pe
    -0.06
    Ar
    -0.06
     drain
    -0.06
     Ser
    -0.06
     viper
    -0.06
    ank
    -0.06
    POSITIVE LOGITS
     kazan
    0.08
     implic
    0.07
     OnTriggerEnter
    0.07
     若要
    0.07
    @index
    0.07
     %@
    0.07
     '{@
    0.07
    jvu
    0.07
    PLEASE
    0.06
     شمالی
    0.06
    Activations Density 0.053%

    No Known Activations