© 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. 93906
    Prev
    Next
    INDEX
    Explanations

    Lua code

    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
    ，但是
    -0.07
     addressed
    -0.07
    �
    -0.06
     iteration
    -0.06
     lobbying
    -0.06
    -condition
    -0.06
     documentation
    -0.06
    83
    -0.06
    Ford
    -0.06
     Regional
    -0.06
    POSITIVE LOGITS
     Iterable
    0.07
    ;;↵↵
    0.06
    帖
    0.06
     評
    0.06
    .unregister
    0.06
    慌
    0.06
    /sc
    0.06
     »↵↵
    0.06
     Pip
    0.06
     Ли
    0.06
    Activations Density 0.020%

    No Known Activations