© 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. 11-RESID-POST-AA
    11. 47795
    Prev
    Next
    INDEX
    Explanations

    chat logs

    np_max-act · gemini-2.0-flash

    Tokens marking the assistant's role or assistant-generated text (i.e., the assistant speaker/turn).

    oai_token-act-pair · gpt-5-mini
    Triggered 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
    Negative Logits
     clone
    -0.08
     formulario
    -0.07
     Negro
    -0.07
    bre
    -0.07
     empleado
    -0.07
     Strings
    -0.07
     элемент
    -0.06
    cence
    -0.06
    .appspot
    -0.06
     IOError
    -0.06
    POSITIVE LOGITS
    useRalativeImagePath
    0.07
     ACTIONS
    0.07
    _(
    0.06
    ighthouse
    0.06
    orderId
    0.06
     pav
    0.06
    践
    0.06
    Much
    0.06
    лиш
    0.06
    限定
    0.06
    Activations Density 0.038%

    No Known Activations