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. 81311
    Prev
    Next
    INDEX
    Explanations

    book summaries

    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
     Ferguson
    -0.06
     McCorm
    -0.06
     Controller
    -0.06
     Міністер
    -0.06
    設備
    -0.06
     Pent
    -0.06
    _Pin
    -0.06
    .Channel
    -0.06
     }}">
    -0.06
     отдел
    -0.06
    POSITIVE LOGITS
     रहन
    0.06
     χα
    0.06
    _co
    0.06
     lanz
    0.06
     kilograms
    0.06
    (s
    0.06
    _Widget
    0.06
    landers
    0.06
    .replace
    0.05
    /f
    0.05
    Activations Density 0.043%

    No Known Activations