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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 77808
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Types
    -0.07
    Nh
    -0.07
     Civ
    -0.07
     stom
    -0.07
    ngo
    -0.06
    ryn
    -0.06
    -case
    -0.06
    Allocator
    -0.06
    Console
    -0.06
     Signature
    -0.06
    POSITIVE LOGITS
    LOCITY
    0.07
    (Parcel
    0.07
     vzděl
    0.06
    soap
    0.06
     FileOutputStream
    0.06
     eksik
    0.06
     توضی
    0.06
     hieronta
    0.06
    _Category
    0.06
     kimse
    0.06
    Activations Density 0.026%

    No Known Activations