© 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. 11-RESID-POST-AA
    11. 37673
    Prev
    Next
    INDEX
    Explanations

    protective

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of protective safety equipment—terms referring to gear or garments (like armor, helmets, vests) designed to shield the body.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions of safety equipment and protective gear.

    oai_token-act-pair · gpt-4o-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
    _aw
    -0.07
     ){↵
    -0.06
     отвер
    -0.06
     примерно
    -0.06
    的大
    -0.06
     Which
    -0.06
    有的
    -0.06
    descriptor
    -0.06
    _CONVERT
    -0.06
    _dic
    -0.06
    POSITIVE LOGITS
     título
    0.06
     guys
    0.06
    تبة
    0.06
    cols
    0.06
     ребенка
    0.06
     numéro
    0.06
     Кра
    0.06
    Processing
    0.06
    semi
    0.06
    uppe
    0.06
    Activations Density 0.033%

    No Known Activations