© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 910
    Prev
    Next
    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash

    This neuron activates on the boilerplate license‐header sentence asking the reader to “contact Oracle if you need additional information or have any questions.”

    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
    ache
    -0.07
     deposits
    -0.06
    蒙
    -0.06
     gaming
    -0.06
    йом
    -0.06
    莱
    -0.06
     scams
    -0.06
    WND
    -0.06
    觉
    -0.06
     одной
    -0.06
    POSITIVE LOGITS
     Arrange
    0.06
    (QtGui
    0.06
     ko
    0.06
     výraz
    0.06
     사실
    0.06
    (true
    0.06
     erre
    0.06
    (Image
    0.06
    _Test
    0.06
    etermin
    0.06
    Activations Density 0.002%

    No Known Activations