© 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. 56352
    Prev
    Next
    INDEX
    Explanations

    PCRE regular expressions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the “PCRE” regular-expression engine (e.g. “PCRE”, “pcre”, “PCRE_UCP,” etc.).

    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
     وهي
    -0.07
     angl
    -0.07
    getOrElse
    -0.06
    _BINDING
    -0.06
     RSA
    -0.06
    Tur
    -0.06
    REC
    -0.06
    bon
    -0.06
    cstdlib
    -0.06
    -desktop
    -0.06
    POSITIVE LOGITS
     single
    0.08
     adaptation
    0.07
     hx
    0.07
    矿
    0.07
     dynamic
    0.07
    (月
    0.06
     gösteren
    0.06
    Ingrese
    0.06
     Digital
    0.06
     bounced
    0.06
    Activations Density 0.008%

    No Known Activations