© 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. 38694
    Prev
    Next
    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash

    This neuron detects expressions of personal desire or preference, especially phrases like “I would like to…” or “I would love to….”

    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
     ConsoleColor
    -0.07
    051
    -0.06
     Williams
    -0.06
     peppers
    -0.06
    Drag
    -0.06
     lets
    -0.06
     Because
    -0.06
     incred
    -0.06
    Because
    -0.06
    .idx
    -0.06
    POSITIVE LOGITS
    ulace
    0.07
    .ptr
    0.07
    (serializer
    0.07
     CAS
    0.07
    cente
    0.07
     трьох
    0.06
    #",
    0.06
     comun
    0.06
    (dev
    0.06
    чя
    0.06
    Activations Density 0.020%

    No Known Activations