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. 104167
    Prev
    Next
    INDEX
    Explanations

    visualize

    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
    departure
    -0.07
     investigation
    -0.07
     button
    -0.06
    504
    -0.06
    _draft
    -0.06
     license
    -0.06
    zk
    -0.06
     eligibility
    -0.06
    (offset
    -0.06
     مرات
    -0.06
    POSITIVE LOGITS
     imagine
    0.07
     kür
    0.07
    ING
    0.07
    UILT
    0.06
    aigned
    0.06
     Gi�
    0.06
     vů
    0.06
    няв
    0.06
    incerely
    0.06
     LOAD
    0.06
    Activations Density 0.018%

    No Known Activations