© 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. 7-RESID-POST-AA
    11. 48961
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    mentions of legal case metadata—especially names and titles of attorneys, judges, and “argued/brief” attributions in court opinions and case captions.

    oai_token-act-pair · gpt-5Triggered 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
     magical
    -0.06
     huyết
    -0.06
    ReadStream
    -0.06
    Internet
    -0.06
    リン
    -0.06
     uống
    -0.06
     manufacturer
    -0.06
     ruler
    -0.06
     Rolex
    -0.06
     UIEdgeInsets
    -0.06
    POSITIVE LOGITS
    ="<
    0.07
     marathon
    0.07
    _TEMPLATE
    0.06
    nr
    0.06
     Newark
    0.06
    :end
    0.06
    elib
    0.06
     الرو
    0.06
     ح
    0.06
     tempList
    0.06
    Activations Density 0.334%

    No Known Activations