© 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. 68272
    Prev
    Next
    INDEX
    Explanations

    Objective-C imports

    np_max-act · gemini-2.0-flash

    The neuron detects short all‐caps letter sequences (module/class prefixes) in code identifiers.

    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
    ilerinin
    -0.07
     Sold
    -0.07
     hậu
    -0.07
    <{↵
    -0.06
     gearbox
    -0.06
    validated
    -0.06
     finals
    -0.06
    Workbook
    -0.06
    endance
    -0.06
     cohorts
    -0.06
    POSITIVE LOGITS
    until
    0.06
    tutorial
    0.06
    _V
    0.06
     Literal
    0.06
    とい
    0.06
    azaar
    0.06
    _Core
    0.06
     และ
    0.05
    oliberal
    0.05
    SelectionMode
    0.05
    Activations Density 0.006%

    No Known Activations