© 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. 101129
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash

    the start of an assistant's reply or the beginning of a structured assistant response (tokens marking the assistant role/response).

    oai_token-act-pair · gpt-5-mini
    Triggered by @yooniel31
    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
    ,e
    -0.07
    .baomidou
    -0.07
     "#"
    -0.07
     chor
    -0.07
     nog
    -0.07
    ğiz
    -0.06
     "["
    -0.06
     페이지
    -0.06
    няття
    -0.06
    δη
    -0.06
    POSITIVE LOGITS
    adin
    0.07
    -master
    0.07
    .Adam
    0.06
     qDebug
    0.06
    (driver
    0.06
    /day
    0.06
     приводит
    0.06
    (reverse
    0.06
     toDate
    0.06
    rita
    0.06
    Activations Density 0.090%

    No Known Activations