© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43135
    Prev
    Next
    INDEX
    Explanations

    Israeli-Palestinian conflict deaths

    np_max-act · gemini-2.0-flash

    The neuron specifically responds to mentions of violent fatality or injury events—words and phrases describing people being shot, killed, wounded, or death counts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     몇
    -0.07
     bác
    -0.06
    DOCUMENT
    -0.06
     awful
    -0.06
    ét
    -0.06
     igen
    -0.06
     ted
    -0.06
     Tento
    -0.06
     За
    -0.06
    ド
    -0.06
    POSITIVE LOGITS
    aphael
    0.07
     repeated
    0.06
     humorous
    0.06
     nearest
    0.06
     Contin
    0.06
     حافظ
    0.06
    hidden
    0.06
    ського
    0.06
     {//
    0.06
     CONST
    0.06
    Activations Density 0.014%

    No Known Activations