© 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. 101700
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    HTML structural / block-level markup tokens (tags and template placeholders that mark major page sections like div, main, header, footer, form, script).

    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
     underneath
    -0.07
    heck
    -0.07
    .AppendFormat
    -0.07
    .social
    -0.06
     +=↵
    -0.06
     Plates
    -0.06
     altar
    -0.06
    .pretty
    -0.06
     스
    -0.06
     Builds
    -0.06
    POSITIVE LOGITS
    imonial
    0.07
    нил
    0.06
    ربی
    0.06
    査
    0.06
     оказ
    0.06
    στο
    0.06
    评论
    0.06
    南
    0.06
    HttpPost
    0.06
     форме
    0.06
    Activations Density 0.023%

    No Known Activations