© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92200
    Prev
    Next
    INDEX
    Explanations

    software libraries and programs

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on ALL‐CAPS words and fragments typical of software license boilerplate, especially uppercase terms in license headers.

    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
     وزن
    -0.07
    тии
    -0.06
     Layer
    -0.06
    urst
    -0.06
     newcomers
    -0.06
    พระ
    -0.06
    Ð
    -0.06
     sunrise
    -0.06
     Criminal
    -0.06
     furnace
    -0.06
    POSITIVE LOGITS
    !',↵
    0.06
    .formData
    0.06
     Gaz
    0.06
    :{↵
    0.06
     COMMENT
    0.06
    .wik
    0.06
     brewing
    0.06
    講
    0.06
    衝
    0.06
    حاد
    0.06
    Activations Density 0.005%

    No Known Activations