© 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. 15-RESID-POST-AA
    11. 28653
    Prev
    Next
    INDEX
    Explanations

    produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     февраля
    -0.07
     Все
    -0.06
     escalating
    -0.06
     hallmark
    -0.06
     insulting
    -0.06
     logically
    -0.06
    Gamma
    -0.06
    안내
    -0.06
     letting
    -0.06
     wall
    -0.06
    POSITIVE LOGITS
     produced
    0.13
     producing
    0.12
     produce
    0.12
     produces
    0.12
     Produced
    0.11
     Production
    0.11
    producer
    0.10
    Production
    0.10
     producer
    0.09
     producers
    0.09
    Activations Density 0.087%

    No Known Activations