© 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. 58929
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron never fires on any of the shown tokens—i.e. it appears inactive (a “dead” neuron) in these examples.

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

    scripts related to server-side programming and file handling.

    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
     nonatomic
    -0.07
     altercation
    -0.07
     스타
    -0.06
    gow
    -0.06
     goof
    -0.06
    мах
    -0.06
     negotiations
    -0.06
    (){
    -0.06
    rush
    -0.06
    .Ship
    -0.06
    POSITIVE LOGITS
    อย
    0.07
    Б
    0.07
     Jeb
    0.06
    (ع
    0.06
     му
    0.06
    /datatables
    0.06
    	lib
    0.06
    (child
    0.06
    .Buffer
    0.06
     kö
    0.06
    Activations Density 0.010%

    No Known Activations