© 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. 11-RESID-POST-AA
    6. 23354
    Prev
    Next
    INDEX
    Explanations

    filtration

    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
     remarkable
    -0.07
    :utf
    -0.07
     bậc
    -0.07
     Mur
    -0.07
    yor
    -0.06
    кта
    -0.06
    .enable
    -0.06
    센터
    -0.06
    	attack
    -0.06
    네요
    -0.06
    POSITIVE LOGITS
     Immigration
    0.07
     pacing
    0.07
     Financial
    0.06
     financial
    0.06
    Inf
    0.06
    ductive
    0.06
     `{
    0.06
    овые
    0.06
    formance
    0.06
    imeters
    0.06
    Activations Density 0.002%

    No Known Activations