© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 105336
    Prev
    Next
    INDEX
    Explanations

    code

    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
    火
    -0.07
    Behaviour
    -0.06
    .Free
    -0.06
     왕
    -0.06
     UIFont
    -0.06
     UITableViewCell
    -0.06
     火
    -0.06
     Něk
    -0.06
     Unreal
    -0.06
    .Flow
    -0.06
    POSITIVE LOGITS
     idiot
    0.07
     shim
    0.06
     portal
    0.06
     Shank
    0.06
    ση
    0.06
    villa
    0.06
     чит
    0.06
     ade
    0.06
    zia
    0.06
     underscores
    0.06
    Activations Density 0.016%

    No Known Activations