© 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. 13043
    Prev
    Next
    INDEX
    Explanations

    comply

    np_max-act · gemini-2.0-flash

    instances of compliance with legal or regulatory requirements.

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

    This neuron detects mentions of compliance (e.g. “comply” and related forms).

    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
     ras
    -0.07
     nebylo
    -0.06
     бес
    -0.06
     �
    -0.06
     parad
    -0.06
    َد
    -0.05
     EST
    -0.05
     кис
    -0.05
    infos
    -0.05
    CTS
    -0.05
    POSITIVE LOGITS
     выполн
    0.07
     выпол
    0.07
     comply
    0.07
     performed
    0.07
     complied
    0.07
    -mile
    0.07
    ↵     ↵
    0.07
    'order
    0.07
    ợ
    0.07
    を行
    0.07
    Activations Density 0.006%

    No Known Activations