© 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. 3-RESID-POST-AA
    11. 121163
    Prev
    Next
    INDEX
    Explanations

    release

    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
    _char
    -0.07
    [-
    -0.07
    hid
    -0.07
    /(
    -0.07
     Mater
    -0.06
    ()
↵
↵
    -0.06
     institution
    -0.06
    None
    -0.06
     />
    -0.06
     institutions
    -0.06
    POSITIVE LOGITS
     releasing
    0.16
     relinqu
    0.10
     rele
    0.09
     releases
    0.08
     release
    0.08
     RELEASE
    0.08
     publi
    0.07
    发布
    0.07
     Release
    0.07
     Bilg
    0.07
    Activations Density 0.035%

    No Known Activations