© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38955
    Prev
    Next
    INDEX
    Explanations

    Scientific measurements

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurement expressions, especially threshold values paired with units (e.g., “<200 cells/μL”).

    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
    出去
    -0.06
    喝
    -0.06
     scour
    -0.06
    270
    -0.06
     하루
    -0.06
     Meredith
    -0.06
    ρων
    -0.06
    _MD
    -0.06
     rend
    -0.06
     cursos
    -0.05
    POSITIVE LOGITS
    split
    0.07
    [now
    0.07
     unite
    0.07
    　　　　　　　　　
    0.07
    BackingField
    0.07
    ($_
    0.06
    .menuStrip
    0.06
    =>"
    0.06
    Trans
    0.06
    ;}
    0.06
    Activations Density 0.024%

    No Known Activations