© 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
    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. 9182
    Prev
    Next
    INDEX
    Explanations

    tables and data

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on tokens that are part of table structures (e.g. table headings, variable names, separators, and headers) in the text.

    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
    DataProvider
    -0.07
    _chance
    -0.06
    .ce
    -0.06
    _CONTROLLER
    -0.06
     Farms
    -0.06
    inci
    -0.06
     blues
    -0.06
     ens
    -0.06
     alarms
    -0.06
    /she
    -0.06
    POSITIVE LOGITS
     steroid
    0.07
     kw
    0.07
     salsa
    0.07
    .mkdir
    0.06
    」↵↵
    0.06
    �
    0.06
     χρόνια
    0.06
     Templates
    0.06
    SW
    0.06
    ->{
    0.06
    Activations Density 0.003%

    No Known Activations