© 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. 54024
    Prev
    Next
    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash

    This neuron detects Java annotation metadata keywords (e.g. Target, ElementType, Retention, Documented) in source 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
    _der
    -0.07
     libros
    -0.07
    web
    -0.06
     XOR
    -0.06
    937
    -0.06
     Ả
    -0.06
    _EXISTS
    -0.06
     scm
    -0.06
    customers
    -0.06
    _expr
    -0.06
    POSITIVE LOGITS
     governing
    0.06
     rough
    0.06
     dangerous
    0.06
     >",
    0.06
    ()}}↵
    0.06
           
↵
    0.06
    hawks
    0.06
    Scott
    0.06
    ус
    0.06
     第一
    0.06
    Activations Density 0.002%

    No Known Activations