© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7132
    Prev
    Next
    INDEX
    Explanations

    Real and imaginary parts

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “Im” or “Re” and the words “imaginary” or “real” when referring to parts of mathematical expressions.

    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
    <s
    -0.06
     faces
    -0.06
     rob
    -0.06
     google
    -0.06
     effects
    -0.06
     seventeen
    -0.06
    google
    -0.06
    :text
    -0.06
    rena
    -0.06
     Keith
    -0.06
    POSITIVE LOGITS
     erkek
    0.07
     підстав
    0.07
     BaseModel
    0.07
    alm
    0.06
    ưới
    0.06
     insiders
    0.06
     necesario
    0.06
     nominee
    0.06
     greeted
    0.06
    ưỡng
    0.06
    Activations Density 0.003%

    No Known Activations