© 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. 127049
    Prev
    Next
    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    The neuron responds to underscore characters, particularly those in license filename/version strings (e.g. "LICENSE_1_0.txt").

    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
    821
    -0.07
     vůbec
    -0.06
     �
    -0.06
     Histogram
    -0.06
     admire
    -0.06
    .org
    -0.06
    ading
    -0.06
    YYYY
    -0.06
     powder
    -0.06
    NEL
    -0.06
    POSITIVE LOGITS
     I
    0.07
    _vertices
    0.07
    _TRNS
    0.07
    _do
    0.06
     vẻ
    0.06
     Revolutionary
    0.06
    .DataGridViewCellStyle
    0.06
    	be
    0.06
     Điện
    0.06
    库
    0.06
    Activations Density 0.001%

    No Known Activations