© 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. 127041
    Prev
    Next
    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash

    The neuron specializes in detecting “Category:” labels that mark the metadata/category section of a Wiki-style article.

    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
    elim
    -0.08
    Christ
    -0.08
     Version
    -0.07
    -0.07
     Time
    -0.07
    Bur
    -0.06
     Bur
    -0.06
    CAST
    -0.06
    /$',
    -0.06
     člově
    -0.06
    POSITIVE LOGITS
    .AutoScale
    0.07
    uky
    0.06
     tricks
    0.06
    .seconds
    0.06
    ounty
    0.06
    .react
    0.06
     слу
    0.06
    .my
    0.06
    田
    0.06
    ुछ
    0.06
    Activations Density 0.005%

    No Known Activations