© 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 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. 38849
    Prev
    Next
    INDEX
    Explanations

    telling someone what to do

    np_max-act · gemini-2.0-flash

    The neuron activates on the infinitival “to” in phrases like “what to do.”

    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
     reunited
    -0.07
    еле
    -0.07
     ds
    -0.07
     infr
    -0.06
    іль
    -0.06
     oo
    -0.06
    -u
    -0.06
    /UIKit
    -0.06
     Abd
    -0.06
     snippet
    -0.06
    POSITIVE LOGITS
    -detail
    0.06
    .Dispatcher
    0.06
    aban
    0.06
     heaven
    0.06
    terminal
    0.06
    -generic
    0.06
    짓
    0.06
    농
    0.06
    "Don
    0.06
    (fe
    0.05
    Activations Density 0.016%

    No Known Activations