© 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. 19-RESID-POST-AA
    6. 73693
    Prev
    Next
    INDEX
    Explanations

    below

    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
    нить
    -0.06
     ruku
    -0.06
     Filtering
    -0.06
    ieee
    -0.06
    MZ
    -0.06
    ictionary
    -0.06
    .pem
    -0.06
     quarry
    -0.06
     kutje
    -0.06
    .nextInt
    -0.05
    POSITIVE LOGITS
     doprav
    0.07
    Elect
    0.07
     competitors
    0.07
     ‘
    0.07
     institution
    0.06
    过来
    0.06
     manufacturers
    0.06
    穿
    0.06
     Liberals
    0.06
    	flags
    0.06
    Activations Density 0.000%

    No Known Activations