© 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. 73617
    Prev
    Next
    INDEX
    Explanations

    delivered

    np_max-act · gemini-2.0-flash

    This neuron detects the standard judicial “opinion of the court was delivered by …” clause that introduces the judge who authored the court’s opinion.

    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
    elijk
    -0.06
    ーナ
    -0.06
     مشک
    -0.06
    ilmek
    -0.06
    複
    -0.06
     hypoc
    -0.06
     rpc
    -0.06
    详情
    -0.06
     输入
    -0.06
     sedan
    -0.06
    POSITIVE LOGITS
     jeux
    0.07
    _BASE
    0.06
    >(*
    0.06
    .mj
    0.06
    <TreeNode
    0.06
     thyroid
    0.06
    ilis
    0.06
     пат
    0.06
     secretion
    0.06
    []
    0.06
    Activations Density 0.001%

    No Known Activations