© 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. 41629
    Prev
    Next
    INDEX
    Explanations

    ite

    np_max-act · gemini-2.0-flash

    This neuron detects the word “cite” as part of case‐citation markers.

    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
     warped
    -0.07
     رق
    -0.06
    霞
    -0.06
     것이다
    -0.06
     نمونه
    -0.06
    нош
    -0.06
    ErrorMessage
    -0.06
     assuming
    -0.06
     Racing
    -0.06
     settings
    -0.06
    POSITIVE LOGITS
    kehr
    0.07
    	Data
    0.06
     civilization
    0.06
    Ide
    0.06
    (Block
    0.06
     spokeswoman
    0.06
    doctype
    0.06
    (getContext
    0.06
     perpetrated
    0.06
    (bit
    0.06
    Activations Density 0.001%

    No Known Activations