© 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. 123415
    Prev
    Next
    INDEX
    Explanations

    lation

    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
     empresas
    -0.07
     viện
    -0.07
     ris
    -0.07
    ança
    -0.06
     Zur
    -0.06
     SME
    -0.06
     energie
    -0.06
    KW
    -0.06
     заліз
    -0.06
     African
    -0.06
    POSITIVE LOGITS
     deflate
    0.14
    lation
    0.10
    lated
    0.08
    lations
    0.07
     Barney
    0.07
    late
    0.06
    LAN
    0.06
     believer
    0.06
    LATED
    0.06
    .AddModelError
    0.06
    Activations Density 0.001%

    No Known Activations