© 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. 41065
    Prev
    Next
    INDEX
    Explanations

    over/through

    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
    TRL
    -0.07
    Convertible
    -0.07
    getCurrent
    -0.07
     setId
    -0.07
     Kart
    -0.07
    .group
    -0.07
    ticker
    -0.06
     Glow
    -0.06
    bridge
    -0.06
    	elem
    -0.06
    POSITIVE LOGITS
     SAS
    0.06
     різ
    0.06
     ming
    0.06
     〃
    0.06
     віз
    0.06
     людини
    0.06
    -details
    0.06
    符合
    0.05
    :none
    0.05
     项
    0.05
    Activations Density 0.810%

    No Known Activations