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. 11-RESID-POST-AA
    6. 81364
    Prev
    Next
    INDEX
    Explanations

    documents

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵            ↵
    -0.07
    eza
    -0.07
    으니
    -0.07
    ublisher
    -0.06
     đó
    -0.06
    ateg
    -0.06
     ya
    -0.06
    ↵                ↵
    -0.06
    .That
    -0.06
     Kob
    -0.06
    POSITIVE LOGITS
    Recipes
    0.06
    oreferrer
    0.06
     Rosenstein
    0.06
     京
    0.06
    LETED
    0.06
    ilingual
    0.06
     textDecoration
    0.06
     ae
    0.06
     Card
    0.06
    248
    0.06
    Activations Density 0.025%

    No Known Activations