© 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. 43794
    Prev
    Next
    INDEX
    Explanations

    Describing people

    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
    utters
    -0.07
    ुपए
    -0.07
    される
    -0.06
    .Xtra
    -0.06
    がある
    -0.06
    _BT
    -0.06
    Whole
    -0.06
    		
↵
↵
    -0.06
     第二
    -0.06
     disconnect
    -0.06
    POSITIVE LOGITS
    -auth
    0.07
     HACK
    0.07
     kurs
    0.07
     autonom
    0.07
    oblins
    0.06
    .hash
    0.06
     existed
    0.06
     gauge
    0.06
     Gr
    0.06
     printf
    0.06
    Activations Density 0.067%

    No Known Activations