© 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. 89001
    Prev
    Next
    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash

    This neuron spotlights the “App” prefix in legal-party labels (as in “Appellant” or “Appellee”) in court‐document 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
    _blocking
    -0.07
     ":"
    -0.07
     partic
    -0.06
    .capture
    -0.06
     pad
    -0.06
     swipe
    -0.06
    _ops
    -0.06
    _TERM
    -0.06
     geography
    -0.06
     rivers
    -0.06
    POSITIVE LOGITS
    漫画
    0.07
    FIRST
    0.06
     Ngoài
    0.06
    Coming
    0.06
    Ngoài
    0.06
     좌
    0.06
    Ả
    0.06
    From
    0.06
    ニﾆ
    0.06
    ，↵↵
    0.06
    Activations Density 0.002%

    No Known Activations