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. 110724
    Prev
    Next
    INDEX
    Explanations

    personal narratives, possibilities

    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
     jet
    -0.07
     Flow
    -0.07
     معروف
    -0.07
     orb
    -0.07
     طبق
    -0.07
     {}
    -0.06
    WebElement
    -0.06
    劃
    -0.06
    .communic
    -0.06
    .getTitle
    -0.06
    POSITIVE LOGITS
     sans
    0.06
    PasswordField
    0.06
     Crypto
    0.06
    Formatter
    0.06
     Ром
    0.06
    esign
    0.06
     pouring
    0.06
    .Enum
    0.06
     restrain
    0.06
    <th
    0.05
    Activations Density 0.073%

    No Known Activations