© 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 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. 11-RESID-POST-AA
    11. 45929
    Prev
    Next
    INDEX
    Explanations

    code/project files

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    하여
    -0.07
    _prefs
    -0.06
    mesinin
    -0.06
    72
    -0.06
    verification
    -0.06
     nějaké
    -0.06
    known
    -0.06
    юк
    -0.06
     Lans
    -0.06
     aired
    -0.06
    POSITIVE LOGITS
    мы
    0.08
     â
    0.07
    ρα
    0.06
    	button
    0.06
     Nos
    0.06
     []
↵
    0.06
     "*.
    0.06
     getSize
    0.06
     smelled
    0.06
    /<?
    0.06
    Activations Density 0.002%

    No Known Activations