© 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. 93613
    Prev
    Next
    INDEX
    Explanations

    milling

    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
    �
    -0.08
     sexo
    -0.07
    /functions
    -0.07
     speeches
    -0.06
     vw
    -0.06
     граф
    -0.06
    form
    -0.06
    01
    -0.06
     форме
    -0.06
     technolog
    -0.06
    POSITIVE LOGITS
     milling
    0.25
    illed
    0.12
    illing
    0.12
    ILLED
    0.09
    覚
    0.07
    치
    0.07
     strategist
    0.07
    -made
    0.06
    elem
    0.06
    Assembler
    0.06
    Activations Density 0.002%

    No Known Activations