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. 15-RESID-POST-AA
    6. 111015
    Prev
    Next
    INDEX
    Explanations

    code logs

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (Book
    -0.07
    conexao
    -0.06
    _rad
    -0.06
     transistor
    -0.06
    (msg
    -0.06
    猛
    -0.06
     striped
    -0.06
    	offset
    -0.06
     midst
    -0.06
    lick
    -0.06
    POSITIVE LOGITS
    xmm
    0.06
    lf
    0.06
     разработ
    0.06
     Peyton
    0.06
     mez
    0.06
    าคม
    0.06
    üf
    0.06
    вать
    0.06
     березня
    0.06
     شاخه
    0.06
    Activations Density 0.014%

    No Known Activations