© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42695
    Prev
    Next
    INDEX
    Explanations

    legal deference

    np_max-act · gemini-2.0-flash

    The neuron flags words and phrases used in legal standard-of-review or deference contexts (e.g. “generally,” “great latitude,” “deferential standard,” “abuse of discretion,” etc.).

    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
     kak
    -0.07
     vanish
    -0.06
    Todd
    -0.06
     Tort
    -0.06
     trấn
    -0.06
     Thompson
    -0.06
    ipes
    -0.06
    ADO
    -0.06
     takes
    -0.06
     improve
    -0.06
    POSITIVE LOGITS
    StringValue
    0.07
    _topology
    0.06
    ilis
    0.06
     Namespace
    0.06
     限
    0.06
    mond
    0.06
    _shader
    0.06
    veedor
    0.06
     cela
    0.06
    lass
    0.06
    Activations Density 0.003%

    No Known Activations