© 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. 92236
    Prev
    Next
    INDEX
    Explanations

    conclusion

    np_max-act · gemini-2.0-flash

    The neuron responds to floating‐point numeric tokens (decimal numbers) 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
    ＼＼
    -0.06
     western
    -0.06
    俄
    -0.06
     sanki
    -0.06
    洋
    -0.06
    akeup
    -0.06
    )row
    -0.06
     preg
    -0.06
    TextNode
    -0.06
     Lý
    -0.06
    POSITIVE LOGITS
    Game
    0.06
     حجم
    0.06
     neuroscience
    0.06
    ۱۹۷
    0.06
    śli
    0.06
    ็นส
    0.06
    ło
    0.06
    ric
    0.06
    ukarı
    0.06
    0.06
    Activations Density 0.009%

    No Known Activations