© 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. 126202
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    This neuron detects discourse markers used to enumerate or transition—words like “One,” “Another,” “Other,” “Many,” “While,” etc.

    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
    	de
    -0.07
     Attention
    -0.06
     dimension
    -0.06
     shading
    -0.06
     Observ
    -0.06
     assertion
    -0.06
     praise
    -0.06
     Addition
    -0.06
     trou
    -0.06
    _dependency
    -0.06
    POSITIVE LOGITS
    扬
    0.07
    زاده
    0.07
    "github
    0.07
    WI
    0.07
     쿠
    0.07
    pci
    0.07
    ázev
    0.07
    tvrt
    0.07
    ;*/↵
    0.07
     unsus
    0.06
    Activations Density 0.013%

    No Known Activations