© 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 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. 38285
    Prev
    Next
    INDEX
    Explanations

    States

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “United States” (including its abbreviations like “U.S.”), flagging references to the United States in the text.

    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
     paying
    -0.06
     detects
    -0.06
    capital
    -0.06
     thugs
    -0.06
     Ctrl
    -0.06
    Threads
    -0.06
    ike
    -0.06
     Betting
    -0.06
    ียนบ
    -0.06
     ilgi
    -0.06
    POSITIVE LOGITS
    ui
    0.07
     upright
    0.07
    人物
    0.06
    �
    0.06
     шп
    0.06
    )、
    0.06
    ())
    0.06
     американ
    0.06
     mj
    0.06
     vardı
    0.06
    Activations Density 0.001%

    No Known Activations