© 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. 126166
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    This neuron detects scholarly citation markers, i.e. bracketed reference labels and associated tokens (e.g. “[@R1]”, numbers, and citation brackets).

    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
    工程
    -0.07
     rope
    -0.07
    _FORCE
    -0.06
    Donald
    -0.06
     Saturday
    -0.06
     Miller
    -0.06
    (defun
    -0.06
    광고
    -0.06
    Ст
    -0.06
    bane
    -0.06
    POSITIVE LOGITS
    elim
    0.07
     ),
↵
    0.07
     tmpl
    0.07
    <![
    0.06
     Geological
    0.06
     kInstruction
    0.06
    (HWND
    0.06
    	onChange
    0.06
    ائی
    0.06
    気持ち
    0.06
    Activations Density 0.047%

    No Known Activations