© 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 EvalsExportsAPI 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. 38422
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    np_max-act · gemini-2.0-flash

    elements related to XML data binding and serialization in programming.

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

    The neuron detects module or namespace declarations and related import/package lines (e.g. XML xmlns attributes, Java/Kotlin `package` or `import` statements).

    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
     performer
    -0.07
     vys
    -0.06
    -application
    -0.06
    itation
    -0.06
    statistics
    -0.06
    (prop
    -0.06
     Beth
    -0.06
     despre
    -0.06
    DataTask
    -0.06
    -war
    -0.06
    POSITIVE LOGITS
    що
    0.07
     mult
    0.07
    angement
    0.07
    pairs
    0.06
     household
    0.06
    ;o
    0.06
    _IM
    0.06
     사항
    0.06
    لسل
    0.06
    _normalize
    0.06
    Activations Density 0.033%

    No Known Activations