© 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. 13682
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash

    This neuron activates on code‐style tokens and syntax (e.g. identifiers, keywords, punctuation) — in other words, it’s looking for programming-language code snippets.

    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
     Dw
    -0.06
     rice
    -0.06
    .duration
    -0.06
    疲
    -0.06
    .Writer
    -0.06
     briefed
    -0.06
    ounter
    -0.06
    iday
    -0.06
     radix
    -0.06
    ]");↵
    -0.06
    POSITIVE LOGITS
     відповід
    0.07
    icontains
    0.06
     абсолют
    0.06
     bilin
    0.06
    (metrics
    0.06
     roadway
    0.06
    ROUND
    0.06
    .neg
    0.06
    álního
    0.06
    ليات
    0.06
    Activations Density 0.477%

    No Known Activations