© 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
    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. 45128
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    Neuron 4 consistently lights up on the word “as” when it’s used to introduce someone’s official capacity or role (e.g. “as the Treasury’s liaison,” “as President,” “as convenor,” etc.).

    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
     Ferd
    -0.07
    기도
    -0.07
     улы
    -0.07
     بص
    -0.07
    �
    -0.06
    เฉ
    -0.06
     فکی
    -0.06
     tep
    -0.06
    ระเบ
    -0.06
    出去
    -0.06
    POSITIVE LOGITS
     prevented
    0.07
    \GeneratedValue
    0.06
    енью
    0.06
    izia
    0.06
     Ports
    0.06
     ↵↵↵
    0.06
     DS
    0.06
    Store
    0.06
    .Date
    0.06
    .Nav
    0.06
    Activations Density 0.010%

    No Known Activations