© 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. 13802
    Prev
    Next
    INDEX
    Explanations

    Nazi

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “Nazi” (and close variants), flagging mentions of the Nazi party or regime.

    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
    orent
    -0.06
     odense
    -0.06
    ा↵↵
    -0.06
    ンガ
    -0.06
     loại
    -0.06
    ाभ
    -0.06
     boredom
    -0.06
     člově
    -0.06
    416
    -0.06
     ngăn
    -0.06
    POSITIVE LOGITS
     Nazi
    0.11
     Nazis
    0.09
    odial
    0.09
     fascist
    0.08
    -Nazi
    0.08
     Conservatives
    0.08
     Viking
    0.07
    Government
    0.07
     parliamentary
    0.07
    -General
    0.06
    Activations Density 0.005%

    No Known Activations