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. 15-RESID-POST-AA
    6. 111116
    Prev
    Next
    INDEX
    Explanations

    hemolysis

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assurance
    -0.07
    oze
    -0.07
    bek
    -0.07
    found
    -0.06
    xAB
    -0.06
     Account
    -0.06
     nada
    -0.06
     кури
    -0.06
    IME
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    全面
    0.07
    建设
    0.07
    ennis
    0.07
     раствор
    0.07
    ıcı
    0.06
     babel
    0.06
     участь
    0.06
     melodies
    0.06
     Anchor
    0.06
     Assault
    0.06
    Activations Density 0.002%

    No Known Activations