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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects XML documentation “summary” tags (the `<summary>`/`</summary>` sections) in code comments.

    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
    _SURFACE
    -0.06
    exports
    -0.06
     ．
    -0.06
    PHPUnit
    -0.06
     آنچه
    -0.06
     Move
    -0.06
     knees
    -0.06
    зем
    -0.06
    ΣΤ
    -0.06
     정부
    -0.06
    POSITIVE LOGITS
     ([[
    0.07
     objekt
    0.07
    害
    0.07
    аті
    0.07
     Fell
    0.06
     Gi
    0.06
    itational
    0.06
     finale
    0.06
    》（
    0.06
     inequality
    0.06
    Activations Density 0.009%

    No Known Activations