© 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. 128520
    Prev
    Next
    INDEX
    Explanations

    Request

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on multi-letter technical acronyms and other specialized uppercase terms (e.g. “FOIA,” “DOJ,” “SDS-PAGE,” “PDR,” “MDR,” species names) rather than common words.

    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
    也有
    -0.07
    Are
    -0.06
     prizes
    -0.06
     Phones
    -0.06
    .query
    -0.06
     Smart
    -0.06
    ासन
    -0.06
     Ideal
    -0.06
     Summary
    -0.06
     Hatch
    -0.06
    POSITIVE LOGITS
    	panic
    0.06
    firstName
    0.06
     propag
    0.06
     рас
    0.06
     někdo
    0.06
     …↵↵
    0.06
     Terrain
    0.06
     ensl
    0.06
     @"↵
    0.06
    χεί
    0.06
    Activations Density 0.321%

    No Known Activations