© 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. 9401
    Prev
    Next
    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash

    The neuron responds to packaging and shipping terms—especially words referring to boxes, cartons, packing, and how an item is presented or packaged.

    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
     obsession
    -0.06
     Pres
    -0.06
     Cand
    -0.06
    Lastly
    -0.06
    (Source
    -0.06
    Ed
    -0.06
    Repositories
    -0.06
    berg
    -0.06
     Před
    -0.06
     swamp
    -0.06
    POSITIVE LOGITS
    tier
    0.08
     dispatcher
    0.07
    UTE
    0.07
    \Contracts
    0.07
    .characters
    0.06
    .calculate
    0.06
     запас
    0.06
     commercially
    0.06
    Symbol
    0.06
    iami
    0.06
    Activations Density 0.010%

    No Known Activations