© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92383
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    This neuron detects the assistant’s standard opening greeting and introductory phrases (e.g., “Hello! I’m here to help…”).

    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
    ramid
    -0.07
    шов
    -0.06
    ????????????????
    -0.06
    ById
    -0.06
     Bard
    -0.06
    Unary
    -0.06
    curr
    -0.06
     бер
    -0.06
     нер
    -0.06
     LIABLE
    -0.06
    POSITIVE LOGITS
     тек
    0.07
     ACK
    0.07
     vaccines
    0.06
    ैं।↵↵
    0.06
    Closing
    0.06
     Carp
    0.06
    "label
    0.06
    SYSTEM
    0.06
    oplayer
    0.06
    selling
    0.06
    Activations Density 0.054%

    No Known Activations