© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    assembly instructions

    np_max-act · gemini-2.0-flash

    This neuron detects low-level embedded-systems terms—particularly opcode/bit/byte/address identifiers and other hardware-interface keywords.

    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
    ضة
    -0.06
     sát
    -0.06
     bones
    -0.06
    cribing
    -0.06
    UMENT
    -0.06
    .attribute
    -0.06
     Perr
    -0.06
    _pas
    -0.06
    -background
    -0.06
     kalan
    -0.06
    POSITIVE LOGITS
    migration
    0.07
    eckého
    0.06
     complains
    0.06
     gossip
    0.06
     Manny
    0.06
    .Popen
    0.06
     Corona
    0.06
    aguay
    0.06
    ürnberg
    0.06
     spole
    0.06
    Activations Density 0.012%

    No Known Activations