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. 51723
    Prev
    Next
    INDEX
    Explanations

    answers

    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
     Emily
    -0.07
     ambition
    -0.06
     dare
    -0.06
     Yup
    -0.06
     range
    -0.06
    NDER
    -0.06
     allowing
    -0.06
     handleChange
    -0.06
     ListBox
    -0.06
    上
    -0.06
    POSITIVE LOGITS
    θηκε
    0.07
    >
    0.06
     acquaintance
    0.06
    AutoresizingMask
    0.06
     acquaint
    0.06
    (":/
    0.06
    "><?
    0.06
     лицо
    0.06
    (rule
    0.06
    <bits
    0.06
    Activations Density 0.024%

    No Known Activations