© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31002
    Prev
    Next
    INDEX
    Explanations

    As

    np_max-act · gemini-2.0-flash

    This neuron fires primarily on the VBA keyword “As,” marking type‐declaration or assignment clauses in the code.

    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
    UpdatedAt
    -0.06
     Halloween
    -0.06
     สม
    -0.06
     در
    -0.06
    ΟΠ
    -0.06
    ニメ
    -0.06
    inish
    -0.05
    -around
    -0.05
    アニメ
    -0.05
    EFF
    -0.05
    POSITIVE LOGITS
    =${
    0.08
     recounts
    0.07
     ise
    0.07
     +++
    0.07
     Generally
    0.06
     VAT
    0.06
    ManagedObject
    0.06
    mai
    0.06
    accom
    0.06
    .setViewportView
    0.06
    Activations Density 0.004%

    No Known Activations