© 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. 109065
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    This neuron activates on first-person pronouns and references (e.g. "I", "my", "mine") indicating the author’s personal experience.

    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
    /misc
    -0.08
    changing
    -0.06
     Q
    -0.06
     hemat
    -0.06
    modifiable
    -0.06
     facilitated
    -0.06
     Lung
    -0.06
    Band
    -0.06
    录
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     Interesting
    0.07
     může
    0.06
    'ils
    0.06
     automate
    0.06
    (&___
    0.06
     surround
    0.06
    ''.
    0.06
    원의
    0.06
    yssey
    0.06
     onCreateView
    0.06
    Activations Density 0.143%

    No Known Activations