© 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. 11-RESID-POST-AA
    11. 51559
    Prev
    Next
    INDEX
    Explanations

    advanced

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isot
    -0.07
    Nothing
    -0.06
     plo
    -0.06
     不
    -0.06
     шт
    -0.06
     comic
    -0.06
     Liqu
    -0.06
     příro
    -0.06
     Soil
    -0.06
     rtrim
    -0.06
    POSITIVE LOGITS
     advance
    0.14
     Advanced
    0.13
     advanced
    0.13
     advancing
    0.13
     Advance
    0.13
     advances
    0.12
    Advance
    0.12
    advance
    0.11
    Adv
    0.10
    Advanced
    0.10
    Activations Density 0.020%

    No Known Activations