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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21214
    Prev
    Next
    INDEX
    Explanations

    hear

    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
     renovations
    -0.07
    23
    -0.07
     различные
    -0.07
     Latitude
    -0.07
    La
    -0.07
     mínimo
    -0.07
    Sizes
    -0.07
     Nova
    -0.07
     ışık
    -0.07
    565
    -0.07
    POSITIVE LOGITS
     hear
    0.14
     heard
    0.11
     hearing
    0.10
     Hearing
    0.10
     Heard
    0.09
    heard
    0.09
     hears
    0.09
     Hear
    0.08
     hurried
    0.07
     learning
    0.07
    Activations Density 0.016%

    No Known Activations