Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 123582
    Prev
    Next
    INDEX
    Explanations

    Short

    np_max-act · gemini-2.0-flash

    elements related to date and time formatting in programming.

    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
     lawyer
    -0.07
    	ROM
    -0.06
    ade
    -0.06
     affected
    -0.06
    ερό
    -0.06
     weed
    -0.06
    :maj
    -0.06
     dose
    -0.06
    _member
    -0.06
     ReactDOM
    -0.06
    POSITIVE LOGITS
     ihre
    0.07
     Holmes
    0.07
     ssize
    0.07
    submitButton
    0.07
    estatus
    0.07
     RoutedEventArgs
    0.06
     laisse
    0.06
    SmartPointer
    0.06
    (exports
    0.06
     Wik
    0.06
    Activations Density 0.004%

    No Known Activations