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. 104168
    Prev
    Next
    INDEX
    Explanations

    sorting algorithms

    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
    .dgv
    -0.08
     Twelve
    -0.07
    pattern
    -0.07
    ='#
    -0.06
     survival
    -0.06
     isLoggedIn
    -0.06
    质
    -0.06
    culate
    -0.06
    GLenum
    -0.06
     pattern
    -0.06
    POSITIVE LOGITS
     pac
    0.07
    _Api
    0.07
     TForm
    0.06
     buoy
    0.06
    *pow
    0.06
    찰
    0.06
     News
    0.06
     �
    0.06
     resemblance
    0.06
    >Main
    0.06
    Activations Density 0.177%

    No Known Activations