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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 43336
    Prev
    Next
    INDEX
    Explanations

    than/as

    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
    ость
    -0.07
     листь
    -0.06
     Gloss
    -0.06
    /fw
    -0.06
    Anything
    -0.06
     diamond
    -0.06
     Sentinel
    -0.06
    中的
    -0.06
     Cliff
    -0.06
     Animation
    -0.05
    POSITIVE LOGITS
    Stopped
    0.06
    MainMenu
    0.06
     Borg
    0.06
    CRM
    0.06
    .hstack
    0.06
     kittens
    0.06
     för
    0.06
    ุณ
    0.06
     τρό
    0.06
     unsuccessfully
    0.06
    Activations Density 0.017%

    No Known Activations