© 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. 19-RESID-POST-AA
    11. 100335
    Prev
    Next
    INDEX
    Explanations

    time

    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
     killer
    -0.06
    sí
    -0.06
    -bg
    -0.06
     تحت
    -0.06
     dile
    -0.06
     Quality
    -0.06
     bcm
    -0.06
    003
    -0.06
     Primary
    -0.06
    AEA
    -0.06
    POSITIVE LOGITS
    .getJSONObject
    0.08
     buena
    0.08
    ='{$
    0.07
    .SceneManagement
    0.07
     tableLayoutPanel
    0.07
    DXVECTOR
    0.07
    "]))↵
    0.06
     послед
    0.06
    üyorum
    0.06
    TIME
    0.06
    Activations Density 0.025%

    No Known Activations