Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41874
    Prev
    Next
    INDEX
    Explanations

    comparisons and numbers

    np_max-act · gemini-2.0-flash

    This neuron specifically responds to JavaScript block-scoped variable declaration keywords like “let” and “const.”

    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
     Entertainment
    -0.07
     мати
    -0.07
     meals
    -0.07
    etherlands
    -0.06
    olidays
    -0.06
     ds
    -0.06
    orsk
    -0.06
    916
    -0.06
    ाच
    -0.06
    写真
    -0.06
    POSITIVE LOGITS
     Доб
    0.07
    全面
    0.07
     terror
    0.06
     террит
    0.06
    options
    0.06
    _SENS
    0.06
     بول
    0.06
    /Error
    0.06
    (pol
    0.06
    gone
    0.06
    Activations Density 0.111%

    No Known Activations