© 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. 55773
    Prev
    Next
    INDEX
    Explanations

    ued

    np_max-act · gemini-2.0-flash

    legal terminology related to court cases and judicial proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires primarily on the word “Argued” in court‐opinion headers indicating when a case was argued.

    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
    createQuery
    -0.07
     Coca
    -0.06
    /access
    -0.06
     currentDate
    -0.06
    UsageId
    -0.06
    imonials
    -0.06
     fizik
    -0.06
     mdi
    -0.06
    поч
    -0.06
     consts
    -0.06
    POSITIVE LOGITS
     curved
    0.07
    生命
    0.07
    VC
    0.07
     centered
    0.06
    �
    0.06
     hect
    0.06
    育
    0.06
     사업
    0.06
     PPP
    0.06
    .setView
    0.06
    Activations Density 0.001%

    No Known Activations