© 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. 79025
    Prev
    Next
    INDEX
    Explanations

    internet forum text

    np_max-act · gemini-2.0-flash

    text indicating the summary/evaluation block (the "Summary:" section and the accompanying fact-check question asking if the summary is consistent).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    OW
    -0.07
     designer
    -0.06
     возрасте
    -0.06
     quarantine
    -0.06
    He
    -0.06
     lessons
    -0.06
    PIO
    -0.06
    ीच
    -0.06
     Wood
    -0.06
     cuisine
    -0.06
    POSITIVE LOGITS
     souha
    0.07
     Alice
    0.06
     συμπ
    0.06
    漢
    0.06
    .setText
    0.06
     undert
    0.06
    quit
    0.06
    .devices
    0.06
    主人
    0.06
     lỗ
    0.06
    Activations Density 0.074%

    No Known Activations