© 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. 15-RESID-POST-AA
    11. 20303
    Prev
    Next
    INDEX
    Explanations

    Common English words/punctuation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。',↵
    -0.09
     mül
    -0.07
     pursuits
    -0.07
    学院
    -0.07
     �
    -0.07
     ROC
    -0.07
     proyecto
    -0.07
     scrut
    -0.07
     정치
    -0.06
    ='')↵
    -0.06
    POSITIVE LOGITS
    ufacturer
    0.06
    .job
    0.06
    .Address
    0.06
    ooled
    0.06
    xef
    0.06
     Larger
    0.06
    により
    0.06
    series
    0.06
    слов
    0.06
    .company
    0.06
    Activations Density 0.000%

    No Known Activations