© 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. 68616
    Prev
    Next
    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of data-loading utilities, especially imports and usage of torch.utils.data (e.g., DataLoader).

    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
    otte
    -0.06
     Saturday
    -0.06
    interest
    -0.06
    mailto
    -0.06
    contact
    -0.06
    orrow
    -0.06
     phosphory
    -0.06
    Barcode
    -0.06
     used
    -0.06
    .detectChanges
    -0.06
    POSITIVE LOGITS
     rv
    0.06
    电子
    0.06
    �
    0.06
    ่าวว
    0.06
     eu
    0.06
    _JS
    0.06
     ευ
    0.06
    .exists
    0.06
    재
    0.06
     cops
    0.06
    Activations Density 0.008%

    No Known Activations