© 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. 17974
    Prev
    Next
    INDEX
    Explanations

    .client

    np_max-act · gemini-2.0-flash

    The neuron detects Python code that creates or configures an AWS S3 client (e.g. calls to boto3.client('s3')).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    Python code snippets related to file uploads to AWS S3 using the Boto3 library.

    oai_token-act-pair · gpt-4o-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
     defendants
    -0.07
    (pattern
    -0.07
     Various
    -0.06
     XX
    -0.06
     Safari
    -0.06
    典
    -0.06
    (feature
    -0.06
    >@
    -0.06
    ฐ
    -0.06
     کل
    -0.06
    POSITIVE LOGITS
    ційних
    0.07
    isLoading
    0.06
    _Value
    0.06
    Clazz
    0.06
    ування
    0.06
    .shows
    0.06
    алог
    0.06
    �
    0.06
    تور
    0.06
     timely
    0.06
    Activations Density 0.009%

    No Known Activations