Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 54191
    Prev
    Next
    INDEX
    Explanations

    code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เฟ
    -0.06
     नर
    -0.06
    rac
    -0.06
     Enum
    -0.06
    	set
    -0.06
    orgot
    -0.06
    sr
    -0.06
     MAV
    -0.06
    _props
    -0.06
    [
    -0.06
    POSITIVE LOGITS
    incible
    0.07
    除了
    0.07
    手に
    0.07
    _->
    0.07
     Losing
    0.06
     kleine
    0.06
    ifikasi
    0.06
    eceğiz
    0.06
    setScale
    0.06
    otionEvent
    0.06
    Activations Density 0.029%

    No Known Activations