© 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. 12436
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron activates on second-person pronouns—especially occurrences of “you” (and to a lesser extent “we”) addressing the reader.

    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
     팬
    -0.06
    usive
    -0.06
    -validator
    -0.06
     дополнитель
    -0.06
     특히
    -0.06
    -inverse
    -0.06
     deductible
    -0.06
    .helper
    -0.06
     Falls
    -0.06
    Bus
    -0.06
    POSITIVE LOGITS
    —he
    0.08
     he
    0.08
    —we
    0.08
     she
    0.07
     He
    0.07
     we
    0.06
    —they
    0.06
     toi
    0.06
     всё
    0.06
    We
    0.06
    Activations Density 0.175%

    No Known Activations