© 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
    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. 765
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron detects formal references to appellate procedure rules and court citation formats (e.g. “Fed. R. App. P. 34(a)(2); 10th Cir. R. 34.1(G)”).

    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
     backlash
    -0.06
    curr
    -0.06
     guild
    -0.06
    UserData
    -0.06
    acement
    -0.06
     Εθν
    -0.06
    .Millisecond
    -0.06
     založ
    -0.06
    ›
    -0.06
     вироб
    -0.06
    POSITIVE LOGITS
     Costs
    0.07
     Ми
    0.06
     th�
    0.06
    _SINGLE
    0.06
    DIG
    0.06
    nine
    0.06
    اختی
    0.06
     trava
    0.06
     Contacts
    0.06
     regardless
    0.06
    Activations Density 0.002%

    No Known Activations