© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    Long texts

    np_max-act · gemini-2.0-flash

    references to children or young people in distress, especially in empathetic contexts involving protection, rescue, safety, or fairness.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    mentions of human hardship or harm—especially crises, oppression, or tragedy—paired with humanitarian concern, rescue, or ethical deliberation

    oai_token-act-pair · gpt-5Triggered 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
    format
    -0.07
    احة
    -0.07
    _prog
    -0.07
     systému
    -0.06
     tarih
    -0.06
    BMI
    -0.06
     musica
    -0.06
     Than
    -0.06
    ництва
    -0.06
    .getTitle
    -0.06
    POSITIVE LOGITS
     LastName
    0.07
     Indexed
    0.07
    вою
    0.07
    slideDown
    0.07
     شکل
    0.06
    -bl
    0.06
     внутр
    0.06
     sev
    0.06
    ，而且
    0.06
     输出
    0.06
    Activations Density 0.104%

    No Known Activations