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

    Neuronpedia

    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. 128346
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron detects parts of chemical formula notation—numbers, parentheses, and element labels (e.g., “1”, “(”, “H”, “3”)—within compound names.

    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
     Signs
    -0.07
    -main
    -0.07
    annis
    -0.07
    online
    -0.07
    -mon
    -0.07
    کر
    -0.07
     ł
    -0.07
     dames
    -0.07
     pm
    -0.07
    agoon
    -0.07
    POSITIVE LOGITS
     Weiter
    0.06
    .Month
    0.06
     (~(
    0.06
    elaide
    0.06
    Our
    0.06
    exter
    0.06
    apult
    0.06
    _UT
    0.06
     disclosing
    0.06
    analyze
    0.06
    Activations Density 0.003%

    No Known Activations