© 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. 51780
    Prev
    Next
    INDEX
    Explanations

    Toxicity/medical advice

    np_max-act · gemini-2.0-flash

    Finds instructions or urgent medical-action recommendations (advice to seek immediate care or specific steps to take) in poisoning or toxic-exposure contexts.

    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
     analyzer
    -0.07
     والد
    -0.07
     burden
    -0.07
    Orden
    -0.07
     utc
    -0.07
    ІІ
    -0.07
     manten
    -0.06
    кра
    -0.06
    _fire
    -0.06
    rica
    -0.06
    POSITIVE LOGITS
    ,'']]],↵
    0.06
    οι
    0.06
    STRUCTION
    0.06
    ,new
    0.06
     gypsum
    0.06
     vielleicht
    0.06
    UGHT
    0.06
     �
    0.06
    .lucene
    0.06
     Sold
    0.06
    Activations Density 0.028%

    No Known Activations