© 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. 19-RESID-POST-AA
    11. 114659
    Prev
    Next
    INDEX
    Explanations

    Groups of girls/young women

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    　　　　　
    -0.07
    etr
    -0.07
    734
    -0.07
    　　　　　　
    -0.06
    .wrapper
    -0.06
    _dep
    -0.06
     tavsiye
    -0.06
    	holder
    -0.06
    -kind
    -0.06
     방문
    -0.06
    POSITIVE LOGITS
     major
    0.07
     afirm
    0.06
    _RAD
    0.06
    TOTAL
    0.06
     Москва
    0.06
    莎
    0.06
     disgrace
    0.06
     epic
    0.06
     Mutation
    0.06
     Addresses
    0.06
    Activations Density 0.006%

    No Known Activations