© 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. 6921
    Prev
    Next
    INDEX
    Explanations

    .now

    np_max-act · gemini-2.0-flash

    Python code snippets related to file manipulation and handling errors for improving code legitimacy and functionality.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects references to obtaining or formatting the current date/time (e.g., calls to datetime.now() and strftime).

    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
    ování
    -0.06
     Мет
    -0.06
     zákaz
    -0.06
    ाहर
    -0.06
     Minerals
    -0.06
    ání
    -0.06
     Tommy
    -0.06
     Dent
    -0.06
    razione
    -0.06
     Films
    -0.06
    POSITIVE LOGITS
     recently
    0.07
     THIS
    0.07
     nitel
    0.07
     bev
    0.06
     getDate
    0.06
     JFrame
    0.06
    ,email
    0.06
     nokt
    0.06
    imestep
    0.06
     вак
    0.06
    Activations Density 0.004%

    No Known Activations