© 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. 89281
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    The neuron fires on code tokens referring to “file” (and its variants like “files” or “fileMask”), i.e. mentions of file-related parameters or directives.

    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
    CI
    -0.06
    ictions
    -0.06
     hills
    -0.06
    RAY
    -0.06
     Zoo
    -0.06
     Jah
    -0.06
     ссыл
    -0.06
     само
    -0.06
    GENER
    -0.06
    olving
    -0.06
    POSITIVE LOGITS
     uniform
    0.07
    _fl
    0.06
     materiál
    0.06
     المر
    0.06
     appel
    0.06
    icação
    0.06
     boss
    0.06
     OnTriggerEnter
    0.06
     kul
    0.06
     departure
    0.06
    Activations Density 0.021%

    No Known Activations