© 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. 29823
    Prev
    Next
    INDEX
    Explanations

    Drug crime rings

    np_max-act · gemini-2.0-flash

    legal terminology and phrases related to court cases and rulings.

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

    This neuron detects formal legal case citations and docket header information in texts.

    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
    定的
    -0.06
    aned
    -0.06
    antanamo
    -0.06
    质
    -0.06
    _apps
    -0.06
    kh
    -0.06
    ********************************************************
    -0.06
    uristic
    -0.06
    icro
    -0.06
    693
    -0.06
    POSITIVE LOGITS
     інтер
    0.06
     Jamie
    0.06
     Rick
    0.06
     dur
    0.06
    (begin
    0.06
     возмож
    0.06
    ्छ
    0.06
    "]="
    0.06
     meteor
    0.06
     Ä
    0.06
    Activations Density 0.021%

    No Known Activations