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. 104055
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
     Franc
    -0.07
    erior
    -0.06
    (weights
    -0.06
     सद
    -0.06
     civilization
    -0.06
    ('
    -0.06
     ");↵
    -0.06
     Television
    -0.06
    очатку
    -0.06
     Soccer
    -0.06
    POSITIVE LOGITS
    /style
    0.06
    getRepository
    0.06
     отнош
    0.06
     lum
    0.06
    �
    0.06
     Cone
    0.06
     Mem
    0.06
     stake
    0.06
    oř
    0.06
    .Des
    0.06
    Activations Density 0.093%

    No Known Activations