© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    Acknowledgement

    np_max-act · gemini-2.0-flash

    This neuron responds to brief positive acknowledgments or approving feedback (e.g. “okay,” “good job,” “thanks,” “I’m impressed”).

    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
     위해
    -0.07
    AZ
    -0.07
     mec
    -0.07
    -find
    -0.07
    원의
    -0.06
    .Keyboard
    -0.06
     IData
    -0.06
     señ
    -0.06
    schemas
    -0.06
     χρη
    -0.06
    POSITIVE LOGITS
     outliers
    0.06
     entrenched
    0.06
    Output
    0.06
    Capt
    0.06
     rushed
    0.06
    View
    0.06
    Matches
    0.06
     jo
    0.06
     Rocket
    0.06
    :Boolean
    0.06
    Activations Density 0.137%

    No Known Activations