© 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. 91175
    Prev
    Next
    INDEX
    Explanations

    Code testing for null values

    np_max-act · gemini-2.0-flash

    This neuron activates on test-assertion method names in code (e.g. toBeDefined, toBe, isEqualTo).

    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
    ERC
    -0.07
     Salmon
    -0.06
     Likely
    -0.06
     mammals
    -0.06
     covenant
    -0.06
    (*)(
    -0.06
    /Application
    -0.06
    (Page
    -0.06
     đàn
    -0.06
     websocket
    -0.06
    POSITIVE LOGITS
    ]?.
    0.06
    /cache
    0.06
    ./
    0.06
    ftp
    0.06
    ]={
    0.06
     LaTeX
    0.06
     />↵
    0.06
    优势
    0.06
    polit
    0.06
    ферен
    0.06
    Activations Density 0.008%

    No Known Activations