© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56875
    Prev
    Next
    INDEX
    Explanations

    GHz

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric measurement tokens—especially decimal values in technical specifications (e.g., clock speeds, frequencies, or sizes).

    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
    شاه
    -0.06
     accur
    -0.06
    NGC
    -0.06
    Illuminate
    -0.06
    estr
    -0.06
    COUNT
    -0.06
    _ring
    -0.06
    labilir
    -0.06
    lifetime
    -0.06
    _ASCII
    -0.06
    POSITIVE LOGITS
    juries
    0.07
    =[
    0.07
     clicking
    0.06
     Wifi
    0.06
    .didReceiveMemoryWarning
    0.06
     folding
    0.06
    sources
    0.06
    'utilisation
    0.06
     crafting
    0.06
    }=
    0.06
    Activations Density 0.003%

    No Known Activations