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

    Neuronpedia

    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. 37940
    Prev
    Next
    INDEX
    Explanations

    Item

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the standalone token “Item,” flagging instances where that exact word appears (often as a label or heading).

    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
    CCCC
    -0.08
     conclusion
    -0.07
     broadcaster
    -0.07
    											↵
    -0.07
    _MODIFIED
    -0.06
     Wald
    -0.06
     psychology
    -0.06
     Bruce
    -0.06
     Force
    -0.06
     انر
    -0.06
    POSITIVE LOGITS
    Item
    0.12
     item
    0.12
     Item
    0.11
     items
    0.10
    StandardItem
    0.10
    Items
    0.09
    ItemId
    0.09
    .getItem
    0.09
    -item
    0.09
     アイ
    0.09
    Activations Density 0.036%

    No Known Activations