© 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. 30939
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find decimal numbers (floating-point numeric values) in the text.

    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
     positives
    -0.08
    體
    -0.08
     Biz
    -0.07
     Mat
    -0.07
     QUI
    -0.07
     credentials
    -0.07
    Effective
    -0.07
    ابط
    -0.07
     Palm
    -0.07
    ắ
    -0.06
    POSITIVE LOGITS
    مارات
    0.07
    _NAME
    0.06
    械
    0.06
     سنة
    0.06
     interess
    0.06
     пере
    0.06
    _Var
    0.06
    ظˆ
    0.06
    .Scale
    0.05
    ’une
    0.05
    Activations Density 0.012%

    No Known Activations