© 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. 92215
    Prev
    Next
    INDEX
    Explanations

    construct

    np_max-act · gemini-2.0-flash

    the neuron activates on PHP constructor method definitions, i.e. occurrences of “__construct.”

    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
    网刊下载次数
    -0.07
     letto
    -0.06
    .TR
    -0.06
    สถาน
    -0.06
     спрос
    -0.06
     Rew
    -0.06
    긔
    -0.06
     satire
    -0.06
    ари
    -0.06
     oranges
    -0.06
    POSITIVE LOGITS
    construct
    0.07
    ;"><
    0.07
     cpp
    0.07
    上传
    0.06
    Church
    0.06
     Residence
    0.06
    -monitor
    0.06
     STR
    0.06
     علاوه
    0.06
    πά
    0.06
    Activations Density 0.001%

    No Known Activations