© 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. 56839
    Prev
    Next
    INDEX
    Explanations

    Do

    np_max-act · gemini-2.0-flash

    The neuron consistently detects the token “Do,” especially when used to begin an imperative or question (e.g. “Do you…,” “Do it…”).

    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
     renovations
    -0.08
     nicer
    -0.07
    (ans
    -0.07
    _requires
    -0.06
    -olds
    -0.06
    Kenn
    -0.06
     kings
    -0.06
     Equals
    -0.06
     lakes
    -0.06
    Winner
    -0.06
    POSITIVE LOGITS
     Do
    0.13
    Do
    0.11
     DO
    0.11
     do
    0.11
    "Do
    0.10
    -do
    0.09
    .Do
    0.09
    do
    0.08
    рія
    0.08
    _DO
    0.08
    Activations Density 0.023%

    No Known Activations