© 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. 90637
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on CamelCase or otherwise capitalized identifiers (e.g. class- or file-names) in code and 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
    Thông
    -0.08
    nk
    -0.07
    anzi
    -0.06
     Sears
    -0.06
    、や
    -0.06
    报告
    -0.06
    iOS
    -0.06
    aml
    -0.06
     يمكن
    -0.06
    =out
    -0.06
    POSITIVE LOGITS
     mondo
    0.07
     yeah
    0.07
     porr
    0.07
     Vote
    0.06
     सल
    0.06
    _APP
    0.06
    地
    0.06
    优势
    0.06
     оборуд
    0.06
     prostituer
    0.06
    Activations Density 0.018%

    No Known Activations