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. 80612
    Prev
    Next
    INDEX
    Explanations

    irt

    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
     afl
    -0.07
    .relu
    -0.07
    .teacher
    -0.07
    .MONTH
    -0.07
    _pk
    -0.06
     решение
    -0.06
    _redirect
    -0.06
    PAIR
    -0.06
     digits
    -0.06
    _ICON
    -0.06
    POSITIVE LOGITS
    ственных
    0.06
     craw
    0.06
     Pour
    0.06
     процесу
    0.06
     peri
    0.06
     edilen
    0.06
     pilgrimage
    0.06
    InRange
    0.05
    DROP
    0.05
     ill
    0.05
    Activations Density 0.013%

    No Known Activations