© 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. 73874
    Prev
    Next
    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash

    This neuron fires on bibliography-style tokens, particularly author‐name placeholders (e.g. “NAME_x”) and the numerical IDs or page numbers that appear in reference entries.

    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
     Yönet
    -0.07
    enderror
    -0.06
    uil
    -0.06
    ानद
    -0.06
    ysl
    -0.06
    ération
    -0.06
    heten
    -0.06
    eki
    -0.06
    orrow
    -0.06
     라이
    -0.06
    POSITIVE LOGITS
    زی
    0.08
    	Client
    0.07
     Та
    0.07
    Eat
    0.07
     clandest
    0.06
     Fee
    0.06
     Paste
    0.06
    欧
    0.06
     solder
    0.06
    .getWidth
    0.06
    Activations Density 0.085%

    No Known Activations