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. 104415
    Prev
    Next
    INDEX
    Explanations

    Code, tests, and reading forums

    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
     Playboy
    -0.08
    POR
    -0.07
    	glColor
    -0.07
     milf
    -0.07
    Cast
    -0.06
     Polymer
    -0.06
    ******↵
    -0.06
     gunshot
    -0.06
     свої
    -0.06
    >K
    -0.06
    POSITIVE LOGITS
     outline
    0.07
     tracked
    0.07
    .leading
    0.07
    elerinin
    0.06
    .org
    0.06
    秘
    0.06
    媒体
    0.06
     xương
    0.06
     männ
    0.06
    活动
    0.06
    Activations Density 0.006%

    No Known Activations