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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    6. 121610
    Prev
    Next
    INDEX
    Explanations

    grant

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coffee
    -0.07
     odom
    -0.06
    Replace
    -0.06
     mond
    -0.06
     Labour
    -0.06
     Respond
    -0.06
     IPs
    -0.06
     Flip
    -0.06
    佳
    -0.06
     ember
    -0.06
    POSITIVE LOGITS
     grants
    0.21
     grant
    0.19
     Grants
    0.16
     Grant
    0.11
    grant
    0.09
     volcanic
    0.07
    ‌
    0.06
    mutable
    0.06
    Grant
    0.06
     orbs
    0.06
    Activations Density 0.003%

    No Known Activations