© 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. 39041
    Prev
    Next
    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash

    The neuron lights up on common function words—especially copulas (“is,” “are”), pronouns (“it”), and discourse markers (“additionally,” “however”)—that introduce or structure explanatory 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
    ्यत
    -0.07
    間
    -0.07
    Uuid
    -0.06
    udent
    -0.06
     вперед
    -0.06
    _Api
    -0.06
    .ru
    -0.06
    冬
    -0.06
     CCP
    -0.06
     Kumar
    -0.06
    POSITIVE LOGITS
     power
    0.07
    endencies
    0.07
     ///↵
    0.07
     상품
    0.07
    TEMP
    0.06
     توسط
    0.06
    IEnumerable
    0.06
     training
    0.06
    롤
    0.06
     Says
    0.06
    Activations Density 0.115%

    No Known Activations