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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41416
    Prev
    Next
    INDEX
    Explanations

    effective

    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
     comrades
    -0.08
     Express
    -0.07
    нуться
    -0.07
     Piano
    -0.06
    downloads
    -0.06
    rocket
    -0.06
     Trees
    -0.06
     هنا
    -0.06
     overriding
    -0.06
    build
    -0.06
    POSITIVE LOGITS
    _BGR
    0.06
    NEY
    0.06
     &[
    0.06
     writable
    0.06
    AGR
    0.06
     일본
    0.06
     χρη
    0.06
     nails
    0.05
    參
    0.05
    ®,
    0.05
    Activations Density 0.001%

    No Known Activations