© 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. 91176
    Prev
    Next
    INDEX
    Explanations

    brackets and commas

    np_max-act · gemini-2.0-flash

    The neuron specifically picks out floating‐point numeric literals (decimal numbers) 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
    Waiting
    -0.07
     C
    -0.06
     ($("#
    -0.06
     Isles
    -0.06
    Arrow
    -0.06
     Myers
    -0.06
     Calder
    -0.06
    /end
    -0.05
     اصفهان
    -0.05
     HDF
    -0.05
    POSITIVE LOGITS
    	flag
    0.08
    otu
    0.07
     Çev
    0.07
     Cancel
    0.07
     Dış
    0.07
     склад
    0.07
    .material
    0.07
    '));↵↵
    0.07
     performed
    0.07
     возраст
    0.07
    Activations Density 0.003%

    No Known Activations