Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 53793
    Prev
    Next
    INDEX
    Explanations

    knee

    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
    	auto
    -0.07
    体
    -0.07
     тим
    -0.06
     cof
    -0.06
     attr
    -0.06
     gym
    -0.06
     体
    -0.06
     side
    -0.06
    Cou
    -0.06
    體
    -0.06
    POSITIVE LOGITS
     FedEx
    0.07
     cherche
    0.07
     pinterest
    0.06
     IOCTL
    0.06
    =in
    0.06
    attempt
    0.06
    utorial
    0.06
    Use
    0.06
     imageUrl
    0.06
    <IActionResult
    0.06
    Activations Density 0.010%

    No Known Activations