© 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. 46139
    Prev
    Next
    INDEX
    Explanations

    cell membrane permeability

    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
    	X
    -0.07
    Ά
    -0.07
    mk
    -0.06
    Types
    -0.06
    base
    -0.06
    о�
    -0.06
    胡
    -0.06
     Type
    -0.06
    -fe
    -0.06
     rack
    -0.06
    POSITIVE LOGITS
     redistribute
    0.07
     prudent
    0.07
     distribution
    0.06
    /vendors
    0.06
     withstand
    0.06
     ██
    0.06
    /trunk
    0.06
     आख
    0.06
    sen
    0.06
    .Optional
    0.06
    Activations Density 0.084%

    No Known Activations