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. 13355
    Prev
    Next
    INDEX
    Explanations

    AP

    np_max-act · gemini-2.0-flash

    This neuron detects the formal header of a Fourth Circuit U.S. Court of Appeals opinion, especially the words in “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
    ‌تواند
    -0.07
    Larry
    -0.07
     کشور
    -0.07
    _tC
    -0.07
     Jur
    -0.07
     Larry
    -0.06
     jsme
    -0.06
    _handling
    -0.06
    Jerry
    -0.06
    home
    -0.06
    POSITIVE LOGITS
     elektrik
    0.07
     Million
    0.06
    ニメ
    0.06
     specifications
    0.06
    fef
    0.06
     traditions
    0.06
    ーー
    0.06
    (im
    0.06
     at
    0.06
    뮤
    0.06
    Activations Density 0.004%

    No Known Activations