© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126210
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects object-oriented code constructs such as class declarations, inheritance/implements keywords, access modifiers, and method signatures.

    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
    	text
    -0.08
     repertoire
    -0.07
     text
    -0.06
    Verse
    -0.06
    Payment
    -0.06
    -request
    -0.06
    write
    -0.06
    .Order
    -0.06
    (script
    -0.06
    eof
    -0.06
    POSITIVE LOGITS
     Brazil
    0.07
    Brazil
    0.07
     concurrent
    0.07
     Acc
    0.07
    __(*
    0.07
    _ls
    0.06
    EMS
    0.06
     пос
    0.06
    葡
    0.06
     Zot
    0.06
    Activations Density 0.016%

    No Known Activations