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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-RESID-POST-AA
    6. 9818
    Prev
    Next
    INDEX
    Explanations

    research/citations

    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
    ‌ای
    -0.07
     Reduced
    -0.07
     Key
    -0.06
     squeezed
    -0.06
     WEEK
    -0.06
    粗
    -0.06
    	time
    -0.06
     Advantage
    -0.06
     rubbed
    -0.06
     Width
    -0.06
    POSITIVE LOGITS
     розта
    0.07
    {!!
    0.07
     unicorn
    0.07
    "';↵
    0.06
    osyal
    0.06
    \",↵
    0.06
    (rgb
    0.06
    imizde
    0.06
    lerine
    0.06
    usted
    0.06
    Activations Density 0.020%

    No Known Activations