© 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. 123658
    Prev
    Next
    INDEX
    Explanations

    ol

    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
     дити
    -0.07
    -winning
    -0.06
    Ho
    -0.06
     Agility
    -0.06
     Improved
    -0.06
     Epic
    -0.06
     filepath
    -0.06
     winning
    -0.06
    得到
    -0.06
     Communic
    -0.06
    POSITIVE LOGITS
    mun
    0.10
     uphol
    0.07
    ol
    0.07
     anymore
    0.06
    _std
    0.06
    xEC
    0.06
     verwenden
    0.06
     immun
    0.06
     lub
    0.06
    شناس
    0.06
    Activations Density 0.006%

    No Known Activations