© 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. 917
    Prev
    Next
    INDEX
    Explanations

    Judge

    np_max-act · gemini-2.0-flash

    The neuron activates on the “Judge” label (and related judge metadata) in judicial opinion headings.

    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
    ัศน
    -0.07
     yapılması
    -0.07
    (mt
    -0.07
    "),
    -0.06
    _csv
    -0.06
     ندار
    -0.06
    %c
    -0.06
     Editing
    -0.06
    "],
    -0.06
    /design
    -0.06
    POSITIVE LOGITS
     publish
    0.07
    (card
    0.07
     Content
    0.06
     симптом
    0.06
     closes
    0.06
     profound
    0.06
    ordinate
    0.06
     elevated
    0.06
     CONTENT
    0.06
     concluding
    0.06
    Activations Density 0.001%

    No Known Activations