© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 43889
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash

    instances of the first-person pronoun "I" (utterances where the speaker refers to themselves).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conversely
    -0.07
    \Seeder
    -0.07
     Rider
    -0.07
     libs
    -0.06
    '=>"
    -0.06
    etype
    -0.06
     fractures
    -0.06
     canadian
    -0.06
    298
    -0.06
    ASSERT
    -0.06
    POSITIVE LOGITS
     للإ
    0.07
     žádné
    0.07
    /base
    0.06
    Dispatcher
    0.06
    ��
    0.06
    Customer
    0.06
     Annunci
    0.06
    _CURRENT
    0.06
    ök
    0.06
    (',
    0.06
    Activations Density 0.004%

    No Known Activations