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. 80816
    Prev
    Next
    INDEX
    Explanations

    know do

    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
    elidir
    -0.07
    missions
    -0.07
    -described
    -0.06
     Twitter
    -0.06
    `:
    -0.06
    ."<
    -0.06
     twitter
    -0.06
     new
    -0.06
    ализ
    -0.06
    ijing
    -0.06
    POSITIVE LOGITS
     cling
    0.07
    _rect
    0.06
     phi
    0.06
    عی
    0.06
    eng
    0.06
     德
    0.06
     petitions
    0.06
    登場
    0.06
    _mass
    0.06
     �
    0.06
    Activations Density 0.025%

    No Known Activations