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. 80812
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    ắ
    -0.07
     граж
    -0.07
     Moh
    -0.06
     Wright
    -0.06
    อว
    -0.06
     Gilles
    -0.06
     persons
    -0.06
     Hence
    -0.06
    -ground
    -0.06
    POSITIVE LOGITS
    уля
    0.06
     cityName
    0.06
    alsex
    0.06
    [next
    0.06
     شاخ
    0.06
    制造
    0.06
    、どう
    0.06
    whose
    0.06
    ez
    0.06
    annon
    0.06
    Activations Density 0.104%

    No Known Activations