© 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. 19-RESID-POST-AA
    6. 70655
    Prev
    Next
    INDEX
    Explanations

    row

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kart
    -0.06
     Perfect
    -0.06
    ήλ
    -0.06
    Products
    -0.06
    AD
    -0.06
     Apt
    -0.06
     Postal
    -0.06
    Fore
    -0.06
    <Value
    -0.06
     thrill
    -0.06
    POSITIVE LOGITS
    lerce
    0.07
     του
    0.06
    ={},
    0.06
    _refresh
    0.06
     =>$
    0.06
    realloc
    0.06
     sorts
    0.06
     impl
    0.06
    Lifecycle
    0.06
     عصر
    0.06
    Activations Density 0.119%

    No Known Activations