Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 80765
    Prev
    Next
    INDEX
    Explanations

    Court dockets

    np_max-act · gemini-2.0-flash
    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
     Finite
    -0.07
     brunette
    -0.07
     extraordin
    -0.06
    _users
    -0.06
     براي
    -0.06
    .Part
    -0.06
    .Black
    -0.06
    _save
    -0.06
    ्यप
    -0.06
     применя
    -0.06
    POSITIVE LOGITS
    828
    0.07
    leo
    0.07
     DNS
    0.07
    dik
    0.07
    thy
    0.06
    edik
    0.06
    ceb
    0.06
    ocurrency
    0.06
    .metric
    0.06
     hindsight
    0.06
    Activations Density 0.001%

    No Known Activations