© 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. 88952
    Prev
    Next
    INDEX
    Explanations

    Signature

    np_max-act · gemini-2.0-flash

    The neuron detects XML elements (and their attributes like Signature, Language, and Value) that encode code‐signature metadata in documentation files.

    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
     readOnly
    -0.07
     imagePath
    -0.06
    _cpus
    -0.06
     tieten
    -0.06
    drops
    -0.06
     pep
    -0.06
     mu
    -0.06
     элемент
    -0.06
    .databind
    -0.06
    _HAS
    -0.06
    POSITIVE LOGITS
    protect
    0.07
     getProperty
    0.07
    grim
    0.06
    (Collection
    0.06
    .MAIN
    0.06
    ző
    0.06
    .kr
    0.06
     Symbol
    0.06
    gil
    0.06
    	Mono
    0.06
    Activations Density 0.002%

    No Known Activations