© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57552
    Prev
    Next
    INDEX
    Explanations

    textile threads

    np_max-act · gemini-2.0-flash

    The neuron activates on technical material‐specification terms and their accompanying numeric or quantitative property values (e.g. permeability, fabric, yarn, filament, density).

    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
    Ch
    -0.06
     grandma
    -0.06
    Tes
    -0.06
    �ng
    -0.06
    -founder
    -0.06
     آمده
    -0.06
     statutes
    -0.06
     deleted
    -0.06
    คราม
    -0.05
     Irene
    -0.05
    POSITIVE LOGITS
     в
    0.07
     všechny
    0.07
     sesso
    0.07
    .orig
    0.07
    �게
    0.07
     rost
    0.07
     rodin
    0.06
    eri
    0.06
     چرا
    0.06
    ble
    0.06
    Activations Density 0.015%

    No Known Activations