© 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. 128896
    Prev
    Next
    INDEX
    Explanations

    various events and publications

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of healthcare and medical topics.

    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
     Certif
    -0.07
     sotto
    -0.06
    圣
    -0.06
     mMap
    -0.06
     Cath
    -0.06
     تست
    -0.06
     selfie
    -0.06
    .other
    -0.06
    _PLATFORM
    -0.06
    	startActivity
    -0.06
    POSITIVE LOGITS
     pathological
    0.07
     UTC
    0.06
     compartments
    0.06
    cker
    0.06
    382
    0.06
    äche
    0.06
    áveis
    0.06
    _t
    0.06
    (ii
    0.06
    _ass
    0.06
    Activations Density 0.365%

    No Known Activations