© 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. 15-RESID-POST-AA
    11. 101596
    Prev
    Next
    INDEX
    Explanations

    see

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confisc
    -0.07
     ख
    -0.06
     фах
    -0.06
    aa
    -0.06
    .maximum
    -0.05
     persecution
    -0.05
     yaşında
    -0.05
     тур
    -0.05
     UNU
    -0.05
     CSR
    -0.05
    POSITIVE LOGITS
    nak
    0.08
    ddf
    0.07
     مشارکت
    0.07
     ned
    0.07
     appearance
    0.07
     жал
    0.07
     tudo
    0.06
    рак
    0.06
    یک
    0.06
    .background
    0.06
    Activations Density 0.015%

    No Known Activations