© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 23539
    Prev
    Next
    INDEX
    Explanations

    careful

    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
    Gain
    -0.07
     flick
    -0.07
     Pais
    -0.06
     significantly
    -0.06
     có
    -0.06
     chant
    -0.06
     nao
    -0.06
     approved
    -0.06
    간
    -0.06
     amazing
    -0.06
    POSITIVE LOGITS
    ufreq
    0.07
    types
    0.06
     آتش
    0.06
     Wishlist
    0.06
    ghest
    0.06
     __________________
    0.06
     regist
    0.06
    .setResult
    0.06
    ürger
    0.06
     getMenu
    0.06
    Activations Density 0.021%

    No Known Activations