© 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. 29494
    Prev
    Next
    INDEX
    Explanations

    casual greetings

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the phrase “how are you” (i.e. user greetings asking about the assistant’s state).

    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
     submissions
    -0.07
    waters
    -0.07
    (System
    -0.06
     courtyard
    -0.06
    완
    -0.06
     зат
    -0.06
     JAVA
    -0.06
    政策
    -0.06
     devote
    -0.06
    wash
    -0.06
    POSITIVE LOGITS
    çiler
    0.06
     ऊ
    0.06
     Hampshire
    0.06
    lena
    0.06
     smith
    0.06
    icians
    0.06
     silk
    0.06
     υπάρχ
    0.06
    Messenger
    0.06
    !==
    0.06
    Activations Density 0.017%

    No Known Activations