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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38184
    Prev
    Next
    INDEX
    Explanations

    Indian government schemes

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of Indian government program acronyms that begin with “PM” (e.g., PMJDY, PMGSY).

    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
    ợi
    -0.08
    щё
    -0.07
     хто
    -0.07
     Corp
    -0.07
    ’den
    -0.07
    with
    -0.06
     response
    -0.06
    (pin
    -0.06
    meyi
    -0.06
     Nach
    -0.06
    POSITIVE LOGITS
     velit
    0.07
    .getStart
    0.06
         ↵
    0.06
    (bool
    0.06
    ilib
    0.06
    ');//
    0.06
    urable
    0.06
    ANGED
    0.06
    ("</
    0.06
    getElementsByTagName
    0.06
    Activations Density 0.011%

    No Known Activations