© 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. 72228
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    np_max-act · gemini-2.0-flash

    This neuron fires on snippets of regular‐expression syntax—particularly digit‐matching escapes (like “\d”), quantifiers (e.g. “{2}”), and character‐class brackets.

    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
    .visitMethodInsn
    -0.07
     Brent
    -0.07
     pundits
    -0.06
    plied
    -0.06
    اسه
    -0.06
     publicly
    -0.06
    ERS
    -0.06
    ѓ
    -0.06
    ulates
    -0.06
     ideals
    -0.06
    POSITIVE LOGITS
    .LayoutInflater
    0.08
    (sql
    0.06
    ैसल
    0.06
    fetchAll
    0.06
    μένη
    0.06
    _wall
    0.06
    \Form
    0.06
    (startTime
    0.06
    ItemId
    0.06
     missing
    0.06
    Activations Density 0.004%

    No Known Activations