© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58670
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX-style numbered markers (e.g. “\#1”, “\#2”, etc.) used for cross‐references or equation/section numbering.

    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
     fgets
    -0.07
    getCurrent
    -0.07
    {text
    -0.07
    	TR
    -0.07
     आत
    -0.06
    英雄
    -0.06
     міжнарод
    -0.06
    公園
    -0.06
    них
    -0.06
    		         
    -0.06
    POSITIVE LOGITS
     Shall
    0.07
     credit
    0.07
     credited
    0.07
    -width
    0.06
     soda
    0.06
     consulta
    0.06
     amber
    0.06
     MAG
    0.06
    ersist
    0.06
    _Session
    0.06
    Activations Density 0.001%

    No Known Activations