© 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. 43148
    Prev
    Next
    INDEX
    Explanations

    negative/serious topics

    np_max-act · gemini-2.0-flash

    The neuron detects tokens associated with disallowed or harmful instructions—i.e. words tied to illegal, unethical, or unhealthy behaviors.

    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
    ισ
    -0.07
    	product
    -0.07
    	world
    -0.06
     RowBox
    -0.06
     crossword
    -0.06
    astr
    -0.06
    jp
    -0.06
     glorious
    -0.06
    serializer
    -0.06
    Players
    -0.06
    POSITIVE LOGITS
    imité
    0.07
     curtains
    0.06
    :true
    0.06
     ε�
    0.06
    _()↵
    0.06
    'action
    0.06
     نوشته
    0.06
     Ear
    0.06
     salary
    0.06
    abilité
    0.06
    Activations Density 0.114%

    No Known Activations