© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8007
    Prev
    Next
    INDEX
    Explanations

    code/math/puzzle responses

    np_max-act · gemini-2.0-flash

    This neuron activates on the assistant’s step‐by‐step mathematical explanations—tokens like “For,” “example,” “therefore,” and other transitional phrases used when laying out a numeric pattern or formula.

    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
     Interestingly
    -0.07
    意义
    -0.07
    RV
    -0.06
     males
    -0.06
     Developers
    -0.06
    native
    -0.06
    axis
    -0.06
     WATER
    -0.06
    Eventually
    -0.06
    xia
    -0.06
    POSITIVE LOGITS
     своїх
    0.07
     connector
    0.06
    AndFeel
    0.06
     úspě
    0.06
    .Formatting
    0.06
    ÔNG
    0.06
     목
    0.06
     orchestra
    0.06
     чист
    0.06
     ψ
    0.06
    Activations Density 0.011%

    No Known Activations