© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 36479
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash

    tokens marking the start of the assistant’s message/response in a chat exchange.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     distr
    -0.07
     crispy
    -0.07
    จะต
    -0.06
     سپس
    -0.06
     آپ
    -0.06
     зависимости
    -0.06
     epile
    -0.06
     xcb
    -0.06
     Arist
    -0.06
    しく
    -0.06
    POSITIVE LOGITS
    ุล
    0.07
     Duterte
    0.07
    ILINE
    0.07
    ологичес
    0.07
    되었다
    0.06
    .nn
    0.06
     Uzbek
    0.06
     Welfare
    0.06
     Vogue
    0.06
    HANDLE
    0.06
    Activations Density 0.101%

    No Known Activations