© 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 EvalsExportsinterp-engineNEWAPI 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. 57969
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    ways to explain the breakdown and meaning of complex words or phrases.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on segments where the text is defining or explaining word meaning—e.g. tokens like “which,” “means,” “understand,” “meaning,” question marks introducing definitions, and related structural markers.

    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
     мали
    -0.07
     hamstring
    -0.07
     七
    -0.06
    .dim
    -0.06
    _dimension
    -0.06
    unction
    -0.06
     autorelease
    -0.06
    Mode
    -0.06
    eldig
    -0.06
     preprocessing
    -0.06
    POSITIVE LOGITS
     ListViewItem
    0.07
     světa
    0.07
     waypoints
    0.06
     Forrest
    0.06
     squarely
    0.06
     توم
    0.06
     ｀
    0.06
     lesbi
    0.06
     Tổng
    0.06
     بن
    0.06
    Activations Density 0.179%

    No Known Activations