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. 104319
    Prev
    Next
    INDEX
    Explanations

    study

    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
    burse
    -0.06
    .uf
    -0.06
     CFG
    -0.06
     Dodgers
    -0.06
    .ch
    -0.06
     Archive
    -0.06
     zurück
    -0.06
    ीफ
    -0.06
    获
    -0.06
    Existing
    -0.06
    POSITIVE LOGITS
    .Players
    0.07
     ян
    0.07
    대의
    0.06
     onAnimation
    0.06
    :'#
    0.06
     banning
    0.06
     sân
    0.06
     mav
    0.06
    ΕΤ
    0.06
    ança
    0.06
    Activations Density 0.016%

    No Known Activations