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. 80956
    Prev
    Next
    INDEX
    Explanations

    partial

    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
    persist
    -0.07
     Shi
    -0.06
     대
    -0.06
     αντι
    -0.06
    Del
    -0.06
     D
    -0.06
    .HttpStatus
    -0.06
    iosa
    -0.06
     متوسط
    -0.06
     сфері
    -0.06
    POSITIVE LOGITS
     histoire
    0.07
     unite
    0.07
    -----------↵
    0.07
    бург
    0.06
     <:
    0.06
    (_.
    0.06
    conomy
    0.06
    énom
    0.06
    =train
    0.06
    ाओ
    0.06
    Activations Density 0.271%

    No Known Activations