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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 93815
    Prev
    Next
    INDEX
    Explanations

    Gift

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coverage
    -0.07
     buckle
    -0.07
     Decom
    -0.07
     attendees
    -0.07
    -night
    -0.07
     uptime
    -0.07
     Aurora
    -0.07
     novice
    -0.07
     truck
    -0.07
     bottom
    -0.07
    POSITIVE LOGITS
     gift
    0.17
     gifts
    0.14
     Gift
    0.13
    Gift
    0.12
     Gifts
    0.10
    gift
    0.09
    ift
    0.09
     gifted
    0.08
    bt
    0.07
    gt
    0.07
    Activations Density 0.005%

    No Known Activations