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. 81333
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    ザ
    -0.07
    Fx
    -0.06
    rent
    -0.06
     Frances
    -0.06
     изменения
    -0.06
     PK
    -0.06
    pz
    -0.06
    달
    -0.06
     rectangles
    -0.06
     ウ
    -0.06
    POSITIVE LOGITS
    asename
    0.07
     recreated
    0.06
    <|begin_of_text|>
    0.06
    -aware
    0.06
     atleast
    0.06
     conquered
    0.06
     [{"
    0.06
    »↵↵
    0.06
     самостоятель
    0.06
    corlib
    0.06
    Activations Density 0.181%

    No Known Activations