© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109329
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    The neuron fires on legal statutes and citations—identifying section numbers, dates, and formal phrasing when quoting or referencing laws.

    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
    nist
    -0.07
    isa
    -0.06
    "].
    -0.06
    DOCKER
    -0.06
    '};↵
    -0.06
    ce
    -0.06
     investing
    -0.06
     Gordon
    -0.06
    .Usuario
    -0.06
    icast
    -0.06
    POSITIVE LOGITS
     війни
    0.07
     كور
    0.07
     Subtract
    0.06
    .getElement
    0.06
     segundos
    0.06
     ए
    0.06
    飞
    0.06
    <SpriteRenderer
    0.06
    TintColor
    0.06
    acf
    0.06
    Activations Density 0.132%

    No Known Activations