© 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. 11-RESID-POST-AA
    11. 46241
    Prev
    Next
    INDEX
    Explanations

    disagreements

    np_max-act · gemini-2.0-flash

    the neuron detects personal pronouns and nearby short function words that mark subjective/commentary language (e.g., I, you, we, they, it, contractions).

    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_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
    izona
    -0.07
     decrypt
    -0.07
    _Settings
    -0.06
    ับค
    -0.06
     Logs
    -0.06
    ındır
    -0.06
    782
    -0.06
    ştır
    -0.06
     csvfile
    -0.05
    Meal
    -0.05
    POSITIVE LOGITS
     northeastern
    0.07
     함
    0.07
    Pref
    0.07
     regress
    0.07
     southeastern
    0.06
     стол
    0.06
     Panels
    0.06
    ्‍
    0.06
     northeast
    0.06
    sns
    0.06
    Activations Density 0.164%

    No Known Activations