© 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. 27-RESID-POST-AA
    11. 22487
    Prev
    Next
    INDEX
    Explanations

    decisions, statements, remarks, critique

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Workflow
    -0.07
     To
    -0.07
    วาง
    -0.07
     Boy
    -0.07
    payload
    -0.06
    tools
    -0.06
    ів
    -0.06
     Sheriff
    -0.06
    аб
    -0.06
    attacks
    -0.06
    POSITIVE LOGITS
     echoing
    0.07
    .JSONObject
    0.07
    	Text
    0.06
    HomePage
    0.06
     +**************
    0.06
    -г
    0.06
     although
    0.06
     بزرگ
    0.06
    .ViewModels
    0.06
    .blank
    0.06
    Activations Density 0.110%

    No Known Activations