© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110367
    Prev
    Next
    INDEX
    Explanations

    GIS/Layers

    np_max-act · gemini-2.0-flash

    technical details and functionalities related to programming and coding in GIS applications.

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

    The neuron fires on occurrences of the “QGIS” token (e.g. import or API references to QGIS).

    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
    ulsive
    -0.07
     Murray
    -0.06
    <TSource
    -0.06
    _movie
    -0.06
    -feed
    -0.06
     voxel
    -0.06
    xm
    -0.06
    �
    -0.06
     Burn
    -0.06
     trouve
    -0.06
    POSITIVE LOGITS
    nid
    0.07
     Đại
    0.07
     �
    0.07
    peak
    0.06
    iterator
    0.06
     simplified
    0.06
     bilin
    0.06
     قدر
    0.06
     Politics
    0.06
    abi
    0.06
    Activations Density 0.001%

    No Known Activations