© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 42362
    Prev
    Next
    INDEX
    Explanations

    medicine and drugs

    np_max-act · gemini-2.0-flash

    mentions of medical/health content — especially medications, treatments, or requests for medical advice.

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     cock
    -0.07
    चन
    -0.07
    trl
    -0.07
    Ptr
    -0.06
    options
    -0.06
     taxis
    -0.06
    _exp
    -0.06
    忠
    -0.06
    inya
    -0.06
    credited
    -0.06
    POSITIVE LOGITS
     Üniversitesi
    0.07
    .П
    0.07
    GenerationStrategy
    0.06
     Київ
    0.06
     सन
    0.06
     isFirst
    0.06
    ้ย
    0.06
     estoy
    0.06
     ส
    0.06
    enler
    0.06
    Activations Density 0.532%

    No Known Activations