© 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. 57885
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron picks out sentence-initial or section-introductory tokens, especially the word “The” (and similar leading words) at the beginnings of sentences.

    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
    resp
    -0.06
    街道
    -0.06
     spatial
    -0.06
    atoon
    -0.06
     foot
    -0.06
    ัฒนา
    -0.06
     promoters
    -0.06
     democrat
    -0.06
    �
    -0.06
    pus
    -0.06
    POSITIVE LOGITS
     Errors
    0.07
     Includes
    0.07
    -Isl
    0.06
    Ệ
    0.06
     QTableWidgetItem
    0.06
     Stability
    0.06
    (opcode
    0.06
    ек
    0.06
    设备
    0.06
    Establish
    0.06
    Activations Density 0.038%

    No Known Activations