© 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. 44670
    Prev
    Next
    INDEX
    Explanations

    Excerpts from varied documents

    np_max-act · gemini-2.0-flash

    The neuron detects chemical compound name endings, in particular the “-ine” suffix.

    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
     шлях
    -0.07
    (folder
    -0.07
    ặ
    -0.07
    ลา
    -0.07
    ственным
    -0.06
    	Camera
    -0.06
     &[
    -0.06
     correctamente
    -0.06
    .ribbon
    -0.06
    Bước
    -0.06
    POSITIVE LOGITS
    icensed
    0.06
    	SELECT
    0.06
     Lois
    0.06
     unzip
    0.06
    (INFO
    0.06
    idepress
    0.06
     Ped
    0.06
    哦
    0.06
    (obs
    0.06
    elease
    0.06
    Activations Density 0.638%

    No Known Activations