© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36669
    Prev
    Next
    INDEX
    Explanations

    ATH

    np_max-act · gemini-2.0-flash

    capitalized proper nouns and titles, especially names of people, places, and creative works.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    ạng
    -0.07
    ident
    -0.06
    .getHost
    -0.06
    ุตบอล
    -0.06
     Byl
    -0.06
    _stdout
    -0.06
     rou
    -0.06
     technik
    -0.06
    .za
    -0.06
    iste
    -0.06
    POSITIVE LOGITS
    RefPtr
    0.07
     divine
    0.06
    LayoutPanel
    0.06
    ="'.$
    0.06
     Adolf
    0.06
     extrav
    0.06
    .symmetric
    0.06
    usr
    0.06
     dokument
    0.05
    ToLower
    0.05
    Activations Density 1.580%

    No Known Activations