© 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. 11-RESID-POST-AA
    6. 104527
    Prev
    Next
    INDEX
    Explanations

    swimming

    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
     Bond
    -0.07
    Pending
    -0.07
     left
    -0.07
     false
    -0.07
    ccione
    -0.07
     halted
    -0.07
     Held
    -0.07
    <Key
    -0.06
    Century
    -0.06
     Placeholder
    -0.06
    POSITIVE LOGITS
     swim
    0.12
     swimming
    0.11
     Swimming
    0.11
     swims
    0.10
     Swim
    0.10
     Shim
    0.07
     넘
    0.07
     вспом
    0.07
     水
    0.07
     Tom
    0.07
    Activations Density 0.006%

    No Known Activations