© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron activates on the `<` and `>` tokens that denote generic type parameters (e.g. in List<…>, Tuple<…>) in code.

    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
     $($
    -0.06
     چیست
    -0.06
    Lin
    -0.06
    ýv
    -0.06
     процед
    -0.06
     "***
    -0.06
     hott
    -0.06
    _timezone
    -0.06
    ení
    -0.06
     EK
    -0.06
    POSITIVE LOGITS
     trademark
    0.07
    	File
    0.06
     NSMutable
    0.06
    UNE
    0.06
     DXGI
    0.06
    놓
    0.06
    weep
    0.06
    载
    0.06
    .Popen
    0.06
    types
    0.06
    Activations Density 0.008%

    No Known Activations