© 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. 7573
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    The neuron fires on the apostrophe-re contraction (as in “they’re” or “you’re”), i.e. the “’re” suffix.

    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
     SEAL
    -0.07
     Ring
    -0.06
    청
    -0.06
     state
    -0.06
     forging
    -0.06
     профес
    -0.06
    ography
    -0.06
    ่า
    -0.06
     Dul
    -0.06
    욕
    -0.06
    POSITIVE LOGITS
    ./
    0.07
     depending
    0.07
    Communic
    0.06
    .Yes
    0.06
    (CharSequence
    0.06
     출연
    0.06
     Atmospheric
    0.06
     日期
    0.06
    decrypt
    0.06
    іття
    0.06
    Activations Density 0.049%

    No Known Activations