© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 121562
    Prev
    Next
    INDEX
    Explanations

    Medical recurrences

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bamb
    -0.07
    aptcha
    -0.07
     Việc
    -0.07
     parameter
    -0.07
     Hak
    -0.06
     advantageous
    -0.06
     expres
    -0.06
     squeez
    -0.06
     interpreter
    -0.06
     Paz
    -0.06
    POSITIVE LOGITS
     recurrent
    0.08
     rematch
    0.07
    urrences
    0.07
    ("↵
    0.06
    	Intent
    0.06
    .getUrl
    0.06
     fighting
    0.06
    meyen
    0.06
     앞
    0.06
    FromClass
    0.06
    Activations Density 0.007%

    No Known Activations