© 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. 128505
    Prev
    Next
    INDEX
    Explanations

    (X

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting snake_case identifiers (like train_test_split, X_train, y_pred) in Python 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
     요청
    -0.06
    '])
↵
    -0.06
     Di
    -0.06
     bạc
    -0.06
     kin
    -0.05
     нада
    -0.05
     дер
    -0.05
    Ver
    -0.05
    Inv
    -0.05
    _words
    -0.05
    POSITIVE LOGITS
    .Support
    0.08
     marked
    0.08
    	cli
    0.07
    -eight
    0.07
     NC
    0.07
    	text
    0.06
     الدول
    0.06
     tuổi
    0.06
    DialogContent
    0.06
     initialState
    0.06
    Activations Density 0.004%

    No Known Activations