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. 81043
    Prev
    Next
    INDEX
    Explanations

    personal stories

    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
    _Custom
    -0.07
    าท
    -0.07
    CLOSE
    -0.06
     кан
    -0.06
     Serg
    -0.06
     HARD
    -0.06
     handful
    -0.06
    Ell
    -0.06
     neighb
    -0.06
    .dir
    -0.06
    POSITIVE LOGITS
     международ
    0.07
    International
    0.07
     Global
    0.07
    .slice
    0.06
    Portály
    0.06
    ymous
    0.06
    undos
    0.06
    ustria
    0.06
    -goal
    0.06
     Shops
    0.06
    Activations Density 0.009%

    No Known Activations