© 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. 54196
    Prev
    Next
    INDEX
    Explanations

    film synopses

    np_max-act · gemini-2.0-flash

    This neuron detects high-frequency English function words—especially articles and short prepositions (e.g. “the,” “a,” “on”).

    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
     CNC
    -0.07
    uyền
    -0.06
    FIELDS
    -0.06
    宋体
    -0.06
    拥
    -0.06
    Am
    -0.06
    овах
    -0.06
    Ini
    -0.06
     posición
    -0.06
     customize
    -0.05
    POSITIVE LOGITS
     accents
    0.07
    _checker
    0.06
     alıyor
    0.06
    plor
    0.06
    _indx
    0.06
     aids
    0.06
     strap
    0.06
    ढ़
    0.06
    fuel
    0.06
    CLS
    0.06
    Activations Density 0.051%

    No Known Activations