© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57933
    Prev
    Next
    INDEX
    Explanations

    copyright

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect the “Copyright” notice in source‐file license headers.

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

    text related to copyright and software licenses.

    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
     declaration
    -0.07
    _scan
    -0.07
     accelerator
    -0.07
    _INFORMATION
    -0.07
    	body
    -0.07
     Dependency
    -0.06
     depiction
    -0.06
    Cod
    -0.06
    _selection
    -0.06
     arc
    -0.06
    POSITIVE LOGITS
     SolidColorBrush
    0.07
     güven
    0.07
     хозя
    0.06
    譜
    0.06
    ToolStrip
    0.06
    \uc
    0.06
     ESPN
    0.06
    ;//
    0.06
    �재
    0.06
    院
    0.06
    Activations Density 0.001%

    No Known Activations