© 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. 124250
    Prev
    Next
    INDEX
    Explanations

    Wars and their effects

    np_max-act · gemini-2.0-flash

    events and themes related to love and longing in the context of war.

    oai_token-act-pair · gpt-4o-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
     multiplayer
    -0.06
    ");↵
    -0.06
     متخصص
    -0.06
     PK
    -0.06
    <n
    -0.06
     Panc
    -0.06
     zm
    -0.06
    (Api
    -0.06
    Catalog
    -0.06
     warriors
    -0.06
    POSITIVE LOGITS
     redes
    0.07
    юр
    0.07
    arpa
    0.07
    llum
    0.06
    	Collection
    0.06
    encies
    0.06
    operations
    0.06
    mods
    0.06
    ическая
    0.06
     Node
    0.06
    Activations Density 0.030%

    No Known Activations