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. 11-RESID-POST-AA
    6. 22044
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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
    Encoding
    -0.07
     Melissa
    -0.07
     claws
    -0.07
     Klopp
    -0.06
    ست
    -0.06
     crimson
    -0.06
     hamstring
    -0.06
    "↵↵↵↵
    -0.06
     colored
    -0.06
     mush
    -0.06
    POSITIVE LOGITS
    Regardless
    0.07
    ET
    0.07
    .ComponentModel
    0.06
    ام
    0.06
    ást
    0.06
     tôi
    0.06
     getProduct
    0.06
    _IRQ
    0.06
    <Scalars
    0.06
    .organ
    0.06
    Activations Density 0.004%

    No Known Activations