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. 80876
    Prev
    Next
    INDEX
    Explanations

    .DataFrame

    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
     Lid
    -0.07
    کش
    -0.07
     Part
    -0.07
    _POSITION
    -0.07
    NST
    -0.06
    _Widget
    -0.06
    bot
    -0.06
    bx
    -0.06
     diferencia
    -0.06
     dal
    -0.06
    POSITIVE LOGITS
     ücret
    0.07
    ertainty
    0.07
     여
    0.06
    ")+
    0.06
     stør
    0.06
     LoginPage
    0.06
    ypass
    0.06
    urope
    0.06
     Susp
    0.06
     OnTrigger
    0.06
    Activations Density 0.002%

    No Known Activations