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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109015
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numbered list or section markers (digits, “#” signs, and related list-heading tokens).

    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
    	result
    -0.06
    _u
    -0.06
     सह
    -0.06
    ,name
    -0.06
     userId
    -0.06
     deputy
    -0.06
    _flux
    -0.06
     cruise
    -0.06
    	array
    -0.06
     теж
    -0.06
    POSITIVE LOGITS
    退
    0.07
     GPA
    0.06
    ол
    0.06
    itaire
    0.06
    'icon
    0.06
    Multiplier
    0.06
    imbus
    0.06
     سطح
    0.06
     Cyan
    0.06
    reflect
    0.06
    Activations Density 0.056%

    No Known Activations