© 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. 54117
    Prev
    Next
    INDEX
    Explanations

    biochemistry

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “operating system,” responding strongly to the words “operating” and “system.”

    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
    937
    -0.07
    ="",
    -0.06
    丸
    -0.06
     financially
    -0.06
     filmpjes
    -0.06
    —you
    -0.06
     Dee
    -0.06
     Thousands
    -0.06
     surgeries
    -0.06
    接着
    -0.06
    POSITIVE LOGITS
     ResultSet
    0.07
    ��
    0.07
    $action
    0.07
                    ↵
    0.07
    +'_
    0.07
    /icons
    0.07
    	AT
    0.06
     appet
    0.06
    self
    0.06
    ги
    0.06
    Activations Density 0.147%

    No Known Activations