© 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. 15-RESID-POST-AA
    11. 111602
    Prev
    Next
    INDEX
    Explanations

    security

    np_max-act · gemini-2.0-flash

    the neuron responds to mentions of physical secure storage and security measures for protecting personal possessions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ียว
    -0.07
     automáticamente
    -0.06
    bish
    -0.06
     lô
    -0.06
     více
    -0.06
     creep
    -0.06
     libert
    -0.06
     Escape
    -0.06
    谈
    -0.06
    Universal
    -0.06
    POSITIVE LOGITS
    default
    0.07
     Erdoğan
    0.07
     Revolution
    0.07
    userInfo
    0.06
    ありがとう
    0.06
    restrict
    0.06
     DataType
    0.06
    alent
    0.06
     куст
    0.06
     distress
    0.06
    Activations Density 0.187%

    No Known Activations