© 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. 88916
    Prev
    Next
    INDEX
    Explanations

    legal documents and acts

    np_max-act · gemini-2.0-flash

    legal terminology and definitions related to regulations and compliance.

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

    The neuron activates on legal‐authority references—statute and code citations, section numbers, and formal mentions of laws or governmental bodies.

    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
    perimental
    -0.07
     jet
    -0.06
    "If
    -0.06
    ad
    -0.06
     cracks
    -0.06
     Aid
    -0.06
    -story
    -0.06
    adh
    -0.06
    _scope
    -0.06
     Machines
    -0.06
    POSITIVE LOGITS
     każ
    0.07
     možnosti
    0.06
     FactoryGirl
    0.06
    <li
    0.06
     半
    0.06
    iền
    0.06
     DATABASE
    0.06
     gmail
    0.06
    сем
    0.06
     пром
    0.06
    Activations Density 0.025%

    No Known Activations