© 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. 89662
    Prev
    Next
    INDEX
    Explanations

    diagrams and figures

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens—especially decimal numbers, measurements, and figure/reference numbers—in technical text.

    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
     books
    -0.07
     manager
    -0.06
     칼
    -0.06
    -sort
    -0.06
    란
    -0.06
     oral
    -0.06
    tests
    -0.06
    thy
    -0.06
    strar
    -0.06
     Khan
    -0.06
    POSITIVE LOGITS
     sque
    0.07
    ضوع
    0.06
    .product
    0.06
     arkadaş
    0.06
     Homeland
    0.06
    listing
    0.06
    _ENABLE
    0.06
     EditorGUI
    0.06
    /mp
    0.06
    	elseif
    0.06
    Activations Density 0.008%

    No Known Activations