© 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. 44654
    Prev
    Next
    INDEX
    Explanations

    indicted

    np_max-act · gemini-2.0-flash

    The neuron detects legal references to formal criminal charging, especially words in the “indict/indictment” family.

    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
     solar
    -0.09
     teacher
    -0.07
     OS
    -0.06
     fclose
    -0.06
    .'.$
    -0.06
     文
    -0.06
    Pixmap
    -0.06
     cost
    -0.06
     Fee
    -0.06
     Berlin
    -0.06
    POSITIVE LOGITS
     indictment
    0.10
     indicted
    0.09
     indict
    0.09
    |(
    0.07
    ={
    0.07
    ,(
    0.06
    heet
    0.06
     initData
    0.06
    죽
    0.06
    ToUpper
    0.06
    Activations Density 0.001%

    No Known Activations