Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126542
    Prev
    Next
    INDEX
    Explanations

    legal arguments

    np_max-act · gemini-2.0-flash

    This neuron detects references to judicial court headings or citations (e.g. “United States Court of Appeals for the Fourth Circuit”).

    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
    >}'
    -0.06
    젠
    -0.06
    smooth
    -0.06
    entieth
    -0.06
    ็นต
    -0.06
    rike
    -0.06
     같다
    -0.06
    tx
    -0.06
    rtype
    -0.06
     sidel
    -0.06
    POSITIVE LOGITS
     searchTerm
    0.09
    OfYear
    0.07
    FormField
    0.07
    ."↵↵↵↵
    0.06
     conqu
    0.06
     ),↵↵
    0.06
    的地
    0.06
    ','$
    0.06
     raid
    0.06
    ).↵
    0.06
    Activations Density 0.019%

    No Known Activations