© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59363
    Prev
    Next
    INDEX
    Explanations

    creation

    np_max-act · gemini-2.0-flash

    The neuron responds to nouns and gerunds that denote processes or acts—especially words like “creation,” “making,” “generation,” or “launch.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     pedestal
    -0.08
     intimacy
    -0.07
    Це
    -0.07
    Rare
    -0.07
     هستند
    -0.07
    ">'+↵
    -0.06
    901
    -0.06
    :block
    -0.06
    /workspace
    -0.06
    _students
    -0.06
    POSITIVE LOGITS
    制作
    0.07
    ेटर
    0.07
    ))/(
    0.07
     SLOT
    0.06
     CharSequence
    0.06
    セット
    0.06
     ""}↵
    0.06
    кування
    0.06
    .collectionView
    0.06
    unsqueeze
    0.06
    Activations Density 0.042%

    No Known Activations