© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13537
    Prev
    Next
    INDEX
    Explanations

    Patriots

    np_max-act · gemini-2.0-flash

    The neuron detects tokens beginning with the prefix “patri,” i.e. words like patriot, patriots, patriotic, patriarch, etc.

    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
     showing
    -0.07
     devised
    -0.07
     bins
    -0.07
     showed
    -0.07
    模
    -0.06
     resulted
    -0.06
     основе
    -0.06
    _Control
    -0.06
    celed
    -0.06
     Sunday
    -0.06
    POSITIVE LOGITS
    atri
    0.11
     patri
    0.10
     Patri
    0.09
     Patriot
    0.09
     Patrick
    0.09
    Patrick
    0.08
     Patriots
    0.08
    玉
    0.08
     patriarch
    0.07
    DatePicker
    0.07
    Activations Density 0.004%

    No Known Activations