© 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. 54375
    Prev
    Next
    INDEX
    Explanations

    Center

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “Center” (or its variant “Centre”) as the start of a named entity.

    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
    oul
    -0.07
    aab
    -0.07
    ash
    -0.06
    Laugh
    -0.06
     Lah
    -0.06
     requ
    -0.06
     Joshua
    -0.06
    DataStream
    -0.06
     Maya
    -0.06
    ولا
    -0.06
    POSITIVE LOGITS
     Center
    0.20
     center
    0.18
    Center
    0.16
     Centre
    0.16
     centers
    0.15
     Centers
    0.14
     centre
    0.14
     CENTER
    0.14
    center
    0.12
    Centre
    0.11
    Activations Density 0.031%

    No Known Activations