© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95607
    Prev
    Next
    INDEX
    Explanations

    requirements

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /account
    -0.07
    提升
    -0.07
     derives
    -0.07
    Mono
    -0.06
     Wifi
    -0.06
    ples
    -0.06
     snowy
    -0.06
    .Mongo
    -0.06
    'utilisateur
    -0.06
    leanup
    -0.06
    POSITIVE LOGITS
     "')
    0.06
    太郎
    0.06
    vertiser
    0.06
    ละ
    0.06
    ंतर
    0.06
    automation
    0.06
     clearTimeout
    0.06
    eus
    0.06
     mơ
    0.06
     않는
    0.06
    Activations Density 0.037%

    No Known Activations