© 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. 7-RESID-POST-AA
    6. 32779
    Prev
    Next
    INDEX
    Explanations

    ine

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     film
    -0.06
     calculation
    -0.06
    app
    -0.06
     Tal
    -0.06
    <Resource
    -0.06
     salt
    -0.06
     Salt
    -0.06
     dismissal
    -0.06
    อส
    -0.06
     localization
    -0.06
    POSITIVE LOGITS
     OPTIONS
    0.07
     Reporter
    0.07
     ere
    0.07
     containerView
    0.07
    _REFERER
    0.07
    rarian
    0.07
    ORN
    0.07
    exc
    0.07
     GOODMAN
    0.06
     crafting
    0.06
    Activations Density 0.001%

    No Known Activations