© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 62188
    Prev
    Next
    INDEX
    Explanations

    style

    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
     ridge
    -0.08
     查看
    -0.07
     cos
    -0.07
     grinder
    -0.07
     ops
    -0.07
     assertion
    -0.06
     perpendicular
    -0.06
     gerçek
    -0.06
    numbers
    -0.06
     authorization
    -0.06
    POSITIVE LOGITS
    ил
    0.07
    ABLE
    0.06
    Styles
    0.06
     Unused
    0.06
    _SAMPLES
    0.06
    abling
    0.06
    ظام
    0.06
    _ED
    0.06
    rogram
    0.06
    ables
    0.06
    Activations Density 0.011%

    No Known Activations