© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23-RESID-POST-AA
    11. 68556
    Prev
    Next
    INDEX
    Explanations

    especially

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     labour
    -0.07
    mapping
    -0.06
    Converter
    -0.06
    -transitional
    -0.06
    lte
    -0.06
    Bootstrap
    -0.06
     angular
    -0.06
    �
    -0.06
     Module
    -0.06
     VBox
    -0.06
    POSITIVE LOGITS
    zzarella
    0.07
    /animations
    0.07
     especially
    0.07
     İngiliz
    0.07
     Vanessa
    0.07
     shy
    0.06
    ncy
    0.06
     notably
    0.06
    prenom
    0.06
    친
    0.06
    Activations Density 0.021%

    No Known Activations