© 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. 109845
    Prev
    Next
    INDEX
    Explanations

    effort

    np_max-act · gemini-2.0-flash

    The neuron detects Portuguese‐language text fragments—especially tokens containing diacritics or common Portuguese morphemes.

    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
    .fasterxml
    -0.07
     зас
    -0.07
     admitting
    -0.06
     bậc
    -0.06
    dtype
    -0.06
     cytok
    -0.06
    -fold
    -0.06
    uition
    -0.05
    ضع
    -0.05
    Enabled
    -0.05
    POSITIVE LOGITS
     노
    0.07
    Remove
    0.07
     libc
    0.07
    　
    0.07
     Peaks
    0.06
    	sh
    0.06
    asha
    0.06
     SwiftUI
    0.06
    RARY
    0.06
     maintained
    0.06
    Activations Density 0.065%

    No Known Activations