© 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. 44773
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical and statistical tokens (counts, percentages, measurements) in demographic or census data.

    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
    енную
    -0.07
    Rua
    -0.06
    [a
    -0.06
    Marks
    -0.06
    France
    -0.06
     Burl
    -0.06
     Latina
    -0.06
    Nothing
    -0.06
     baskets
    -0.06
    note
    -0.06
    POSITIVE LOGITS
     ngăn
    0.08
     anzeigen
    0.07
     pon
    0.07
    -clean
    0.06
    .source
    0.06
    이비
    0.06
     ход
    0.06
    ́
    0.06
    ?>"><
    0.06
     espos
    0.06
    Activations Density 0.001%

    No Known Activations