© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130014
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron activates on polite expressions of gratitude—e.g. “thank you,” “thanks,” and related thank-you phrases.

    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
     FALSE
    -0.06
     pork
    -0.06
     titles
    -0.06
     Tate
    -0.06
    ampton
    -0.06
     offices
    -0.06
     helper
    -0.06
     bank
    -0.06
    azar
    -0.06
     CASE
    -0.06
    POSITIVE LOGITS
     underst
    0.06
     йому
    0.06
     karak
    0.06
    -HT
    0.06
     clap
    0.06
    Mid
    0.06
    .'.
    0.06
     Ost
    0.06
     foreseeable
    0.06
     Reload
    0.06
    Activations Density 0.075%

    No Known Activations