© 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. 65230
    Prev
    Next
    INDEX
    Explanations

    illegal

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to illegal, unethical, or otherwise disallowed actions (e.g., “illegal,” “unethical,” “law,” “activities”).

    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
    ギ
    -0.07
     media
    -0.06
     пример
    -0.06
    Nov
    -0.06
     کارگرد
    -0.06
    $total
    -0.06
    interest
    -0.06
    анию
    -0.06
     interesse
    -0.06
    :*
    -0.06
    POSITIVE LOGITS
    nj
    0.07
     arcpy
    0.06
     smr
    0.06
     tento
    0.06
     switched
    0.06
     flooded
    0.06
    =""><
    0.06
     departed
    0.06
    bedPane
    0.06
    BlockSize
    0.06
    Activations Density 0.011%

    No Known Activations