© 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. 126870
    Prev
    Next
    INDEX
    Explanations

    .idea

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the identifier “idea,” in particular when it appears in package or import paths (e.g. com.android.tools.idea…).

    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
     dương
    -0.07
     asia
    -0.06
    908
    -0.06
    orna
    -0.06
    .try
    -0.06
     alloys
    -0.06
    -icons
    -0.06
    ertas
    -0.06
    774
    -0.06
     Renault
    -0.06
    POSITIVE LOGITS
     下载
    0.07
     Lowe
    0.07
     Incre
    0.07
     dissolve
    0.06
    提升
    0.06
     Vac
    0.06
     εγκα
    0.06
    üsseldorf
    0.06
     деп
    0.06
     ultr
    0.06
    Activations Density 0.002%

    No Known Activations